Hugging Face's logo

IRSC
/
ELDOR-checkpoints

Model card Files
xet
 Community
ELDOR-checkpoints / summary.md
kangnicui2's picture
kangnicui2
Upload summary.md with huggingface_hub
1e7a53e verified
preview code
|
raw
history blame
101 kB

Experiment Suite Summary

Metric Notes

  • Main comparison metric: test_miou_present.
  • Complexity is reported as gflops (2 FLOPs per MAC convention).
  • params_m/gflops/latency are inference-time model complexity numbers (independent of whether some modules were frozen during training).
  • MCPNet upstream default schedule: 80k iters (configs/_base_/schedules/schedule_80k.py).
  • PPMambaSeg upstream defaults vary by dataset; PPMamba configs are typically 40-50 epochs (e.g., LoveDA=40, Vaihingen=50).

Ranking (chronological order)

status model backbone loss venue params_m gflops latency_ms_1x3x512x512 peak_vram_gb test_miou_present test_macro_f1_present test_oa_fg test_miou best_val_miou best_val_miou_present
completed DeepLabV3+ ConvNeXt-Tiny ce+dice ECCV2018 29.3108 75.9139 4.4970 0.2086 0.3895 0.5260 0.7189 0.2782 0.3292 0.3545
completed DeepLabV3+ ConvNeXt-Tiny focal+dice ECCV2018 29.3108 75.9139 4.4970 0.2086 0.3735 0.5068 0.7048 0.2668 0.3325 0.3581
completed DeepLabV3+ ConvNeXt-Tiny weighted_ce+dice ECCV2018 29.3108 75.9139 4.4970 0.2086 0.3766 0.5193 0.6840 0.2690 0.3482 0.3750
completed DeepLabV3+ ResNet-50 ce+dice ECCV2018 26.6809 73.5922 2.8963 0.2300 0.3662 0.4897 0.7092 0.2817 0.3379 0.3379
completed DeepLabV3+ ResNet-50 focal+dice ECCV2018 26.6809 73.5922 2.8963 0.2300 0.3515 0.4819 0.7000 0.2929 0.3415 0.3461
completed DeepLabV3+ ResNet-50 weighted_ce+dice ECCV2018 26.6809 73.5922 2.8963 0.2300 0.3438 0.4755 0.6951 0.2644 0.3427 0.3427
completed UPerNet Swin-Tiny ce+dice ECCV2018 59.8371 472.1168 22.6344 0.5306 0.3371 0.4651 0.6729 0.2593 0.2873 0.2873
completed OCRNet HRNet-W48 ce+dice ECCV2020 70.3653 325.3542 61.4944 0.5052 0.2722 0.3954 0.5735 0.2268 0.2954 0.2954
completed SegFormer MiT-B2 ce+dice NeurIPS2021 27.3574 121.9349 8.3250 0.5432 0.3222 0.4594 0.6484 0.2301 0.3231 0.3480
completed SegFormer MiT-B2 focal+dice NeurIPS2021 27.3574 121.9349 8.3250 0.5432 0.3332 0.4760 0.6385 0.2380 0.3250 0.3501
completed SegFormer MiT-B2 weighted_ce+dice NeurIPS2021 27.3574 121.9349 8.3250 0.5432 0.4010 0.5297 0.7163 0.3084 0.3423 0.3423
completed Mask2Former ResNet-50 set_matching_ce+mask+dice CVPR2022 44.0064 133.2907 17.4630 0.4213 0.2985 0.4285 0.6561 0.2985 0.3033 0.3033
completed SegNeXt MSCAN-Tiny ce+dice NeurIPS2022 4.2285 12.6449 9.2612 0.1673 0.2682 0.3884 0.6065 0.1916 0.2895 0.2896
completed Afformer AFFormer-Base ce+dice AAAI2023 2.9690 8.5730 7.4704 0.1691 0.3047 0.4362 0.6389 0.2176 0.2928 0.3153
completed EfficientViT-Seg EfficientViT-B2 ce+dice ICCV2023 15.2802 18.3156 6.4212 0.1213 0.3799 0.5065 0.7258 0.2713 0.3444 0.3444
completed EfficientViT-Seg EfficientViT-B2 focal+dice ICCV2023 15.2802 18.3156 6.4212 0.1213 0.3693 0.5086 0.6781 0.2638 0.3520 0.3790
completed EfficientViT-Seg EfficientViT-B2 weighted_ce+dice ICCV2023 15.2802 18.3156 6.4212 0.1213 0.3790 0.5181 0.7154 0.2707 0.3565 0.3840
completed SeaFormer SeaFormer-Base ce+dice ICLR2023 8.5838 3.4741 12.4666 0.1700 0.3117 0.4408 0.6392 0.2398 0.3116 0.3116
completed CGRSeg EfficientFormerV2-B ce+dice ECCV2024 19.0799 7.5003 14.4088 0.2569 0.2679 0.3961 0.5844 0.1913 0.3054 0.3054
completed PEM ResNet-50 set_matching_ce+mask+dice CVPR2024 35.5313 60.6003 11.5152 0.3881 0.2789 0.4011 0.6502 0.2789 0.2549 0.2549
- --- REMOTE SENSING SEGMENTATION METHODS --- - - - - - - - - - - - - -
completed FarSeg ResNet-50 ce (native) CVPR2020 31.3698 94.1161 3.9675 0.2414 0.3564 0.4726 0.7130 0.2970 0.2989 0.2989
completed BANet ResT-Lite ce+dice RS2021 12.8608 31.3805 4.6832 0.1026 0.2926 0.4147 0.6535 0.2250 0.2779 0.2992
completed ABCNet ResNet-18 ce+dice+aux_ce ISPRSJPRS2021 13.9645 32.3860 4.0397 0.1004 0.3145 0.4302 0.6831 0.2621 0.3070 0.3070
completed MANet ResNet-50 ce+dice TGRS2022 35.8629 109.6158 4.7794 0.3940 0.3711 0.4922 0.6862 0.3093 0.3147 0.3147
completed MANet ResNet-50 weighted_ce+dice TGRS2022 35.8629 109.6158 4.7794 0.3940 0.3828 0.5228 0.6759 0.2734 0.3079 0.3316
running MANet ResNet-50 focal+dice TGRS2022 - - - - - - - - - -
completed UNetFormer ResNet-18 ce+dice+aux_ce ISPRSJPRS2022 11.7259 23.5509 5.8413 0.0899 0.3941 0.5152 0.7276 0.3284 0.3388 0.3388
completed UNetFormer ResNet-18 weighted_ce+dice+aux_ce ISPRSJPRS2022 11.7259 23.5509 5.8413 0.0899 0.3566 0.4931 0.6811 0.2743 0.3275 0.3275
completed UNetFormer ResNet-18 focal+dice+aux_focal ISPRSJPRS2022 11.7259 23.5509 5.8413 0.0899 0.3765 0.4989 0.7182 0.3137 0.3314 0.3314
completed DC-Swin Swin-Small ce+dice TGRS2022 66.9503 144.3925 23.4351 0.3567 0.2971 0.4173 0.6584 0.2476 0.2884 0.2884
completed A2FPN ResNet-18 ce+dice IJRS2022 12.1620 27.1366 3.8670 0.2150 0.3688 0.4834 0.7335 0.3073 0.3085 0.3085
completed A2FPN ResNet-18 weighted_ce+dice IJRS2022 12.1620 27.1366 3.8670 0.2150 0.3720 0.5107 0.7094 0.2657 0.2959 0.3187
completed A2FPN ResNet-18 focal+dice IJRS2022 12.1620 27.1366 3.8670 0.2150 0.3363 0.4602 0.6659 0.2802 0.3027 0.3027
completed LoGCAN ResNet-50 ce+aux_ce (native) ICASSP2023 30.9157 99.2253 6.0530 0.2298 0.3108 0.4081 0.7474 0.2590 0.2951 0.2951
completed SACANet HRNet-W32 ce+aux_ce (native) ICME2023 30.2704 115.9042 21.8449 0.3073 0.3294 0.4557 0.6573 0.2534 0.2985 0.3215
completed FarSeg++ MiT-B2 ce (native) TGRS2023 32.5566 95.0793 13.5646 0.2784 0.3062 0.4358 0.6669 0.2187 0.3049 0.3284
completed DOCNet HRNet-W32 ce+aux_ce (native) GRSL2024 39.1269 395.3173 21.2797 0.4263 0.3147 0.4398 0.6785 0.2421 0.2772 0.2772
completed RS3Mamba ResNet-18 + VMamba-Tiny ce+dice GRSL2024 43.3254 78.5912 11.6012 0.4624 0.2385 0.3080 0.7257 0.1987 0.1559 0.1559
completed RS3Mamba ResNet-18 + VMamba-Tiny weighted_ce+dice GRSL2024 43.3254 78.5912 11.6012 0.4624 0.3068 0.4280 0.6519 0.2556 0.2313 0.2313
completed RS3Mamba ResNet-18 + VMamba-Tiny focal+dice GRSL2024 43.3254 78.5912 11.6012 0.4624 0.2399 0.3125 0.7251 0.1999 0.1910 0.1910
running PyramidMamba Swin-Base ce+dice JAG2025 - - - - - - - - - -
completed LoGCAN++ RepViT-M2.3 ce+aux_ce (native) TGRS2025 25.1927 74.3696 17.1870 0.2225 0.2264 0.3066 0.6353 0.2264 0.2264 0.2264
completed MF-Mamba HRNet-W18 ce+dice TGRS2025 11.2729 38.9439 20.5415 0.1326 0.3001 0.4242 0.6376 0.2501 0.3039 0.3039
completed MCPNet ResNet-50 ce (native) TGRS2025 45.1516 110.9866 6.8683 0.3518 0.3293 0.4489 0.7103 0.2533 0.3063 0.3063
completed MCPNet ResNet-50 ce+dice TGRS2025 45.1516 110.9866 6.8683 0.3518 0.3056 0.4267 0.6680 0.2183 0.3051 0.3051
completed MCPNet ResNet-50 weighted_ce+dice TGRS2025 45.1516 110.9866 6.8683 0.3518 0.3193 0.4552 0.6405 0.2281 0.2954 0.3181
completed MCPNet ResNet-50 focal+dice TGRS2025 45.1516 110.9866 6.8683 0.3518 0.3233 0.4448 0.6898 0.2487 0.3027 0.3027
completed PPMambaSeg swsl-ResNet-18 ce+dice GRSL2025 21.7049 45.9905 11.2803 0.3103 0.3520 0.4780 0.6683 0.2934 0.3362 0.3362
running PPMambaSeg swsl-ResNet-18 weighted_ce+dice GRSL2025 - - - - - - - - - -
running PPMambaSeg swsl-ResNet-18 focal+dice GRSL2025 - - - - - - - - - -
- --- REMOTE SENSING SEGMENTATION WITH VFM --- - - - - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) ce+dice NeurIPS2023 - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) focal+dice NeurIPS2023 - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) weighted_ce+dice NeurIPS2023 - - - - - - - - - -
completed SAM_RS ABCNet + SAM priors seg+bdy+obj (native) TGRS2024 13.9645 32.3860 2.8004 0.1014 0.2964 0.4098 0.6573 0.2470 0.3104 0.3104
completed SAM_RS CMTFNet + SAM priors seg+bdy+obj (native) TGRS2024 30.0727 68.6118 6.5588 0.3354 0.2916 0.4084 0.6598 0.2243 0.2909 0.2909
completed SAM_RS FTUNetFormer + SAM priors seg+bdy+obj (native) TGRS2024 96.1376 64.7028 15.0411 0.4364 0.2922 0.4094 0.6871 0.2435 0.2859 0.2859
completed SAM_RS UNetFormer + SAM priors seg+bdy+obj (native) TGRS2024 11.6880 23.5509 4.4489 0.0880 0.3241 0.4452 0.6839 0.2700 0.2971 0.2971
completed RSAM-Seg SAM-ViT-B (frozen encoder) ce+dice RS2025 98.5875 247.0546 15.1369 0.6103 0.3263 0.4472 0.6978 0.2510 0.2959 0.2959
completed RSAM-Seg SAM-ViT-B (frozen encoder) focal+dice RS2025 98.5875 247.0546 15.1369 0.6103 0.3450 0.4642 0.7430 0.2654 0.2841 0.2841
completed RSAM-Seg SAM-ViT-B (frozen encoder) weighted_ce+dice RS2025 98.5875 247.0546 15.1369 0.6103 0.3696 0.5085 0.6978 0.2640 0.3128 0.3333
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) ce+dice ICLR2025 83.8976 191.8167 10.7092 0.9487 0.2422 0.3510 0.6193 0.1863 0.2082 0.2242
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) focal+dice ICLR2025 83.8976 191.8167 10.7092 0.9487 0.2351 0.3438 0.6158 0.1809 0.2124 0.2288
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) weighted_ce+dice ICLR2025 83.8976 191.8167 10.7092 0.9487 0.2207 0.3235 0.5938 0.1577 0.2160 0.2326
running SAM2.1 Hiera-B+ (full finetune, msfpn) ce+dice ICLR2025 - - - - - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) focal+dice ICLR2025 - - - - - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) weighted_ce+dice ICLR2025 - - - - - - - - - -
completed SESSRS A2FPN (ce+dice) t1/t2 search + postprocess TGRS2025 12.1620 27.1366 7.0712 0.2150 0.3702 0.4848 0.7338 0.3085 0.3094 0.3094
completed SESSRS A2FPN (focal) t1/t2 search + postprocess TGRS2025 12.1620 27.1366 7.7431 0.2150 0.3374 0.4613 0.6663 0.2812 0.3035 0.3035
completed SESSRS A2FPN (weighted) t1/t2 search + postprocess TGRS2025 12.1620 27.1366 7.2436 0.2150 0.3745 0.5139 0.7098 0.2675 0.2984 0.3214
completed SESSRS ABCNet (ce+dice+aux) t1/t2 search + postprocess TGRS2025 13.9645 32.3860 84.0456 0.1004 0.3154 0.4311 0.6835 0.2629 0.3078 0.3078
completed SESSRS BANet (ce+dice) t1/t2 search + postprocess TGRS2025 12.8608 31.3805 12.8044 0.1026 0.2937 0.4161 0.6536 0.2259 0.2791 0.3006
completed SESSRS MANet (ce+dice) t1/t2 search + postprocess TGRS2025 35.8629 109.6158 12.4290 0.3940 0.3604 0.4820 0.6775 0.3004 0.3162 0.3162
completed SESSRS UNetFormer (ce+dice) t1/t2 search + postprocess TGRS2025 11.7259 23.5509 9.2771 0.0899 0.3958 0.5167 0.7279 0.3298 0.3399 0.3399
completed SESSRS UNetFormer (focal) t1/t2 search + postprocess TGRS2025 11.7259 23.5509 9.5268 0.0899 0.3873 0.5091 0.7195 0.3228 0.3406 0.3406
completed SESSRS UNetFormer (weighted) t1/t2 search + postprocess TGRS2025 11.7259 23.5509 9.7288 0.0899 0.3578 0.4943 0.6816 0.2752 0.3286 0.3286

Training / Validation Summary

status model backbone loss venue best_val_miou_epoch best_val_miou best_val_miou_present_epoch best_val_miou_present val_bestckpt_macro_f1_present val_bestckpt_oa_fg
completed DeepLabV3+ ConvNeXt-Tiny ce+dice ECCV2018 31 0.3292 31 0.3545 0.4635 0.7756
completed DeepLabV3+ ConvNeXt-Tiny focal+dice ECCV2018 62 0.3325 62 0.3581 0.4709 0.7464
completed DeepLabV3+ ConvNeXt-Tiny weighted_ce+dice ECCV2018 29 0.3482 29 0.3750 0.4984 0.7134
completed DeepLabV3+ ResNet-50 ce+dice ECCV2018 12 0.3379 12 0.3379 0.4502 0.7204
completed DeepLabV3+ ResNet-50 focal+dice ECCV2018 65 0.3415 12 0.3461 0.4657 0.7042
completed DeepLabV3+ ResNet-50 weighted_ce+dice ECCV2018 23 0.3427 23 0.3427 0.4627 0.7224
completed UPerNet Swin-Tiny ce+dice ECCV2018 31 0.2873 31 0.2873 0.3876 0.6733
completed OCRNet HRNet-W48 ce+dice ECCV2020 47 0.2954 47 0.2954 0.4008 0.6782
completed SegFormer MiT-B2 ce+dice NeurIPS2021 32 0.3231 32 0.3480 0.4556 0.7732
completed SegFormer MiT-B2 focal+dice NeurIPS2021 17 0.3250 17 0.3501 0.4640 0.7633
completed SegFormer MiT-B2 weighted_ce+dice NeurIPS2021 2 0.3423 60 0.3423 0.4523 0.7439
completed Mask2Former ResNet-50 set_matching_ce+mask+dice CVPR2022 40 0.3033 40 0.3033 0.4128 0.7111
completed SegNeXt MSCAN-Tiny ce+dice NeurIPS2022 75 0.2895 75 0.2896 0.3805 0.7429
completed Afformer AFFormer-Base ce+dice AAAI2023 76 0.2928 76 0.3153 0.4038 0.7610
completed EfficientViT-Seg EfficientViT-B2 ce+dice ICCV2023 13 0.3444 64 0.3444 0.4580 0.7550
completed EfficientViT-Seg EfficientViT-B2 focal+dice ICCV2023 50 0.3520 50 0.3790 0.5034 0.7380
completed EfficientViT-Seg EfficientViT-B2 weighted_ce+dice ICCV2023 68 0.3565 68 0.3840 0.5164 0.7507
completed SeaFormer SeaFormer-Base ce+dice ICLR2023 37 0.3116 37 0.3116 0.4020 0.7642
completed CGRSeg EfficientFormerV2-B ce+dice ECCV2024 56 0.3054 56 0.3054 0.3963 0.7577
completed PEM ResNet-50 set_matching_ce+mask+dice CVPR2024 57 0.2549 57 0.2549 0.3483 0.6476
- --- REMOTE SENSING SEGMENTATION METHODS --- - - - - - - - - -
completed FarSeg ResNet-50 ce (native) CVPR2020 10 0.2989 10 0.2989 0.4017 0.6666
completed BANet ResT-Lite ce+dice RS2021 31 0.2779 31 0.2992 0.3969 0.7172
completed ABCNet ResNet-18 ce+dice+aux_ce ISPRS2021 12 0.3070 12 0.3070 0.4087 0.7066
completed MANet ResNet-50 ce+dice TGRS2022 31 0.3147 31 0.3147 0.4108 0.6763
completed MANet ResNet-50 weighted_ce+dice TGRS2022 31 0.3079 31 0.3316 0.4447 0.6724
running MANet ResNet-50 focal+dice TGRS2022 - - - - - -
completed UNetFormer ResNet-18 ce+dice+aux_ce ISPRS2022 5 0.3388 5 0.3388 0.4375 0.7641
completed UNetFormer ResNet-18 weighted_ce+dice+aux_ce ISPRS2022 25 0.3275 25 0.3275 0.4329 0.7243
completed UNetFormer ResNet-18 focal+dice+aux_focal ISPRS2022 5 0.3314 5 0.3314 0.4291 0.7378
completed DC-Swin Swin-Small ce+dice TGRS2022 - 0.2884 - 0.2884 0.3846 0.6994
completed A2FPN ResNet-18 ce+dice IJRS2022 18 0.3085 18 0.3085 0.4068 0.6811
completed A2FPN ResNet-18 weighted_ce+dice IJRS2022 12 0.2959 12 0.3187 0.4405 0.6435
completed A2FPN ResNet-18 focal+dice IJRS2022 2 0.3027 2 0.3027 0.4050 0.6693
completed LoGCAN ResNet-50 ce+aux_ce (native) ICASSP2023 80 0.2951 80 0.2951 0.3798 0.7522
completed SACANet HRNet-W32 ce+aux_ce (native) ICME2023 29 0.2985 29 0.3215 0.4191 0.6878
completed FarSeg++ MiT-B2 ce (native) TGRS2023 65 0.3049 65 0.3284 0.4341 0.7590
completed DOCNet HRNet-W32 ce+aux_ce (native) GRSL2024 17 0.2772 17 0.2772 0.3665 0.6567
completed RS3Mamba ResNet-18 + VMamba-Tiny ce+dice GRSL2024 2 0.1559 2 0.1559 0.2179 0.6601
completed RS3Mamba ResNet-18 + VMamba-Tiny weighted_ce+dice GRSL2024 3 0.2313 3 0.2313 0.3219 0.6845
completed RS3Mamba ResNet-18 + VMamba-Tiny focal+dice GRSL2024 2 0.1910 2 0.1910 0.2521 0.7198
running PyramidMamba Swin-Base ce+dice JAG2025 - - - - - -
completed LoGCAN++ RepViT-M2.3 ce+aux_ce (native) TGRS2025 17 0.2264 17 0.2264 0.3066 0.6353
completed MF-Mamba HRNet-W18 ce+dice TGRS2025 54 0.3039 54 0.3039 0.3988 0.6506
completed MCPNet ResNet-50 ce (native) TGRS2025 58 0.3063 58 0.3063 0.4044 0.7179
completed MCPNet ResNet-50 ce+dice TGRS2025 - 0.3051 - 0.3051 0.3952 0.7140
completed MCPNet ResNet-50 weighted_ce+dice TGRS2025 23 0.2954 23 0.3181 0.4178 0.7706
completed MCPNet ResNet-50 focal+dice TGRS2025 33 0.3027 33 0.3027 0.3944 0.7601
completed PPMambaSeg swsl-ResNet-18 ce+dice GRSL2025 31 0.3362 31 0.3362 0.4369 0.7208
running PPMambaSeg swsl-ResNet-18 weighted_ce+dice GRSL2025 - - - - - -
running PPMambaSeg swsl-ResNet-18 focal+dice GRSL2025 - - - - - -
- --- REMOTE SENSING SEGMENTATION WITH VFM --- - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) ce+dice NeurIPS2023 - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) focal+dice NeurIPS2023 - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) weighted_ce+dice NeurIPS2023 - - - - - -
completed SAM_RS ABCNet + SAM priors seg+bdy+obj (native) TGRS2024 22 0.3104 22 0.3104 0.4073 0.6960
completed SAM_RS CMTFNet + SAM priors seg+bdy+obj (native) TGRS2024 74 0.2909 74 0.2909 0.3898 0.6481
completed SAM_RS FTUNetFormer + SAM priors seg+bdy+obj (native) TGRS2024 44 0.2859 44 0.2859 0.3777 0.7297
completed SAM_RS UNetFormer + SAM priors seg+bdy+obj (native) TGRS2024 40 0.2971 40 0.2971 0.3934 0.6894
completed RSAM-Seg SAM-ViT-B (frozen encoder) ce+dice RS2025 19 0.2959 19 0.2959 0.3907 0.7304
completed RSAM-Seg SAM-ViT-B (frozen encoder) focal+dice RS2025 28 0.2841 28 0.2841 0.3742 0.7546
completed RSAM-Seg SAM-ViT-B (frozen encoder) weighted_ce+dice RS2025 13 0.3128 65 0.3333 0.4506 0.6948
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) ce+dice ICLR2025 57 0.2082 57 0.2242 0.3053 0.6757
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) focal+dice ICLR2025 56 0.2124 56 0.2288 0.3108 0.6903
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) weighted_ce+dice ICLR2025 56 0.2160 56 0.2326 0.3165 0.6928
running SAM2.1 Hiera-B+ (full finetune, msfpn) ce+dice ICLR2025 - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) focal+dice ICLR2025 - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) weighted_ce+dice ICLR2025 - - - - - -
completed SESSRS A2FPN (ce+dice) t1/t2 search + postprocess TGRS2025 - 0.3094 - 0.3094 0.4078 0.6813
completed SESSRS A2FPN (focal) t1/t2 search + postprocess TGRS2025 - 0.3035 - 0.3035 0.4059 0.6699
completed SESSRS A2FPN (weighted) t1/t2 search + postprocess TGRS2025 - 0.2984 - 0.3214 0.4445 0.6442
completed SESSRS ABCNet (ce+dice+aux) t1/t2 search + postprocess TGRS2025 - 0.3078 - 0.3078 0.4096 0.7069
completed SESSRS BANet (ce+dice) t1/t2 search + postprocess TGRS2025 - 0.2791 - 0.3006 0.3987 0.7175
completed SESSRS MANet (ce+dice) t1/t2 search + postprocess TGRS2025 - 0.3162 - 0.3162 0.4125 0.6766
completed SESSRS UNetFormer (ce+dice) t1/t2 search + postprocess TGRS2025 - 0.3399 - 0.3399 0.4388 0.7646
completed SESSRS UNetFormer (focal) t1/t2 search + postprocess TGRS2025 - 0.3406 - 0.3406 0.4403 0.7242
completed SESSRS UNetFormer (weighted) t1/t2 search + postprocess TGRS2025 - 0.3286 - 0.3286 0.4342 0.7247

Per-Class IoU Tables (Completed + Running)

Validation (best checkpoint)

  • Source: /deac/csc/yangGrp/cuij/GoldMDD/experiments/diagnostics/val_per_class_iou_completed_models_present_only.csv
  • Heatmap: /deac/csc/yangGrp/cuij/GoldMDD/experiments/diagnostics/val_per_class_iou_completed_models_heatmap.png
  • Classes shown: 13 (GT-present in val)
  • Running rows are placeholders (-) until eval artifacts are generated.

General segmentation methods

status model backbone loss val_miou_present Building Mining raft Primary Forest Heavy machinery Water bodies Agricultural crop Compact mounds Gravel mounds Grass Type1 regen Type2 regen Bare ground Sluice
completed DeepLabV3+ ConvNeXt-Tiny ce+dice 0.3545 0.2133 0.0865 0.8066 0.2182 0.6615 0.6747 0.0392 0.1743 0.8533 0.3079 0.23 0.3278 0.0155
completed DeepLabV3+ ConvNeXt-Tiny focal+dice 0.3581 0.2864 0.1416 0.7751 0.1851 0.6372 0.6956 0.0379 0.2392 0.8532 0.2776 0.2053 0.3186 0.0026
completed DeepLabV3+ ConvNeXt-Tiny weighted_ce+dice 0.375 0.3155 0.1156 0.7247 0.232 0.6333 0.6592 0.0653 0.4249 0.836 0.3016 0.2258 0.2937 0.0471
completed DeepLabV3+ ResNet-50 ce+dice 0.3379 0.3138 0.0 0.7313 0.1287 0.5083 0.6617 0.1065 0.343 0.8274 0.3056 0.219 0.2469 0.0
completed DeepLabV3+ ResNet-50 focal+dice 0.3461 0.2902 0.166 0.7753 0.1166 0.5847 0.7103 0.0254 0.1847 0.8476 0.2739 0.185 0.2795 0.0
completed DeepLabV3+ ResNet-50 weighted_ce+dice 0.3427 0.3405 0.238 0.7561 0.1523 0.4819 0.6178 0.066 0.2589 0.8272 0.3118 0.1478 0.2571 0.0
completed UPerNet Swin-Tiny ce+dice 0.2873 0.228 0.0356 0.6775 0.0 0.6036 0.3316 0.0475 0.161 0.8584 0.2953 0.2135 0.2827 0.0
completed OCRNet HRNet-W48 ce+dice 0.2954 0.1587 0.0 0.7014 0.0 0.6124 0.3595 0.1218 0.3642 0.7617 0.27 0.1971 0.2929 0.0
completed SegFormer MiT-B2 ce+dice 0.348 0.2508 0.0295 0.8176 0.0639 0.5704 0.6613 0.0935 0.3357 0.8436 0.2786 0.2757 0.3028 0.0001
completed SegFormer MiT-B2 focal+dice 0.3501 0.2831 0.1476 0.7984 0.0965 0.589 0.5631 0.0615 0.4209 0.8524 0.2692 0.1864 0.2827 0.0
completed SegFormer MiT-B2 weighted_ce+dice 0.3423 0.3146 0.0892 0.7779 0.0 0.6919 0.3261 0.1256 0.4907 0.7972 0.3384 0.1524 0.346 0.0
completed Mask2Former ResNet-50 set_matching_ce+mask+dice 0.3033 0.177 0.1985 0.7404 0.0 0.4916 0.6668 0.1032 0.1376 0.7004 0.2342 0.2501 0.2438 0.0
completed SegNeXt MSCAN-Tiny ce+dice 0.2896 0.2184 0.0398 0.7696 0.0 0.6707 0.2777 0.0474 0.0208 0.8416 0.2989 0.2856 0.2937 0.0
completed Afformer AFFormer-Base ce+dice 0.3153 0.2372 0.0157 0.789 0.0 0.6877 0.617 0.0559 0.0213 0.8253 0.2894 0.2516 0.3091 0.0
completed EfficientViT-Seg EfficientViT-B2 ce+dice 0.3444 0.2052 0.2415 0.7877 0.008 0.6405 0.5567 0.0854 0.4163 0.7731 0.2403 0.2298 0.2928 0.0
completed EfficientViT-Seg EfficientViT-B2 focal+dice 0.379 0.2128 0.2106 0.7713 0.0638 0.612 0.664 0.1235 0.5 0.841 0.2837 0.1836 0.2769 0.1841
completed EfficientViT-Seg EfficientViT-B2 weighted_ce+dice 0.384 0.3164 0.2363 0.7856 0.1793 0.5556 0.691 0.0851 0.3464 0.8189 0.2521 0.1972 0.3088 0.2189
completed SeaFormer SeaFormer-Base ce+dice 0.3116 0.1769 0.0 0.797 0.0 0.6495 0.6236 0.0463 0.0917 0.8057 0.3248 0.2391 0.2965 0.0
completed CGRSeg EfficientFormerV2-B ce+dice 0.3054 0.2614 0.0312 0.7958 0.0 0.6478 0.5404 0.0554 0.0285 0.8311 0.2562 0.2336 0.2889 0.0
completed PEM ResNet-50 set_matching_ce+mask+dice 0.2549 0.0876 0.1619 0.6831 0.0 0.4522 0.5112 0.0184 0.0492 0.7612 0.1856 0.1671 0.2366 0.0
completed RS3Mamba ResNet-18 + VMamba-Tiny ce+dice 0.1559 0.0 0.0 0.7344 0.0 0.3705 0.0 0.0025 0.0 0.4074 0.1691 0.0971 0.2458 0.0
completed RS3Mamba ResNet-18 + VMamba-Tiny weighted_ce+dice 0.2313 0.0809 0.0 0.7845 0.0 0.6007 0.3012 0.021 0.1857 0.4663 0.1959 0.1665 0.2043 0.0
completed RS3Mamba ResNet-18 + VMamba-Tiny focal+dice 0.191 0.0 0.0 0.8065 0.0 0.5853 0.0144 0.0136 0.0093 0.5123 0.208 0.0748 0.2593 0.0
completed MCPNet ResNet-50 ce (native) 0.3063 0.1876 0.0 0.7344 0.0 0.5528 0.5225 0.0191 0.3239 0.8451 0.3155 0.2103 0.2701 0.0
completed MCPNet ResNet-50 ce+dice 0.3051 0.1041 0.0 0.7422 0.0 0.5736 0.6592 0.0187 0.3616 0.839 0.228 0.2075 0.2332 0.0
completed MCPNet ResNet-50 weighted_ce+dice 0.3181 0.1041 0.0782 0.8021 0.0 0.606 0.5622 0.0677 0.2102 0.8293 0.3378 0.2475 0.2906 0.0
completed MCPNet ResNet-50 focal+dice 0.3027 0.1376 0.0 0.7836 0.0 0.6151 0.5854 0.0696 0.1374 0.8352 0.2712 0.2263 0.2731 0.0
completed PPMambaSeg swsl-ResNet-18 ce+dice 0.3362 0.2672 0.0 0.7544 0.0 0.5425 0.6552 0.0694 0.4968 0.8348 0.225 0.2576 0.2673 0.0
running PPMambaSeg swsl-ResNet-18 weighted_ce+dice - - - - - - - - - - - - - -
running PPMambaSeg swsl-ResNet-18 focal+dice - - - - - - - - - - - - - -

Remote sensing segmentation methods

status model backbone loss val_miou_present Building Mining raft Primary Forest Heavy machinery Water bodies Agricultural crop Compact mounds Gravel mounds Grass Type1 regen Type2 regen Bare ground Sluice
completed FarSeg ResNet-50 ce (native) 0.2989 0.2645 0.0 0.6644 0.0 0.6033 0.5275 0.0018 0.3353 0.7271 0.2688 0.2193 0.2743 0.0
completed BANet ResT-Lite ce+dice 0.2992 0.1944 0.0 0.7519 0.0 0.5869 0.5615 0.1578 0.1029 0.809 0.2574 0.1872 0.2811 0.0
completed ABCNet ResNet-18 ce+dice+aux_ce 0.307 0.2142 0.0 0.7417 0.0 0.5475 0.5567 0.0974 0.2884 0.8265 0.2429 0.1955 0.2807 0.0
completed MANet ResNet-50 ce+dice 0.3147 0.3122 0.0 0.6773 0.0 0.6197 0.6587 0.0235 0.3137 0.835 0.1884 0.1847 0.2778 0.0
completed MANet ResNet-50 weighted_ce+dice 0.3316 0.3612 0.1092 0.6824 0.0911 0.5321 0.6414 0.0341 0.4564 0.7893 0.1841 0.1735 0.242 0.0139
running MANet ResNet-50 focal+dice - - - - - - - - - - - - - -
completed UNetFormer ResNet-18 ce+dice+aux_ce 0.3388 0.3298 0.0 0.8087 0.0 0.5549 0.6044 0.0268 0.4637 0.8287 0.3045 0.187 0.2958 0.0
completed UNetFormer ResNet-18 weighted_ce+dice+aux_ce 0.3275 0.1742 0.1195 0.7759 0.0 0.5172 0.6792 0.0672 0.4487 0.7557 0.2766 0.1497 0.293 0.0
completed UNetFormer ResNet-18 focal+dice+aux_focal 0.3314 0.2914 0.0 0.7808 0.0 0.4692 0.7022 0.0275 0.4293 0.8336 0.2948 0.1898 0.2893 0.0
completed DC-Swin Swin-Small ce+dice 0.2884 0.1573 0.0 0.7263 0.0 0.6021 0.467 0.095 0.1835 0.8402 0.2047 0.1979 0.275 0.0
completed A2FPN ResNet-18 ce+dice 0.3085 0.2414 0.0 0.6982 0.0 0.5217 0.6605 0.058 0.3145 0.8409 0.2018 0.177 0.2971 0.0
completed A2FPN ResNet-18 weighted_ce+dice 0.3187 0.3033 0.0675 0.652 0.0774 0.3458 0.6664 0.1585 0.3381 0.7892 0.2379 0.1567 0.273 0.0768
completed A2FPN ResNet-18 focal+dice 0.3027 0.3418 0.0 0.6944 0.0 0.4618 0.5967 0.024 0.3705 0.764 0.2357 0.163 0.2831 0.0
completed LoGCAN ResNet-50 ce+aux_ce (native) 0.2951 0.1831 0.0 0.778 0.0 0.6095 0.5597 0.0195 0.0079 0.8367 0.3021 0.2517 0.2875 0.0
completed SACANet HRNet-W32 ce+aux_ce (native) 0.3215 0.2771 0.0 0.6927 0.0 0.5465 0.6559 0.0007 0.3922 0.8508 0.2916 0.2007 0.2709 0.0
completed FarSeg++ MiT-B2 ce (native) 0.3284 0.2062 0.1642 0.7977 0.0067 0.6212 0.5303 0.037 0.3087 0.8464 0.2526 0.2149 0.2834 0.0
completed DOCNet HRNet-W32 ce+aux_ce (native) 0.2772 0.2603 0.0 0.6923 0.0 0.5262 0.6034 0.0 0.1738 0.8157 0.1898 0.1209 0.221 0.0
running PyramidMamba Swin-Base ce+dice - - - - - - - - - - - - - -
completed LoGCAN++ RepViT-M2.3 ce+aux_ce (native) 0.2264 0.0874 0.0 0.677 0.0 0.4898 0.2945 0.0016 0.0581 0.7983 0.1796 0.1272 0.2298 0.0
completed MF-Mamba HRNet-W18 ce+dice 0.3039 0.2858 0.0 0.6708 0.0 0.505 0.6674 0.0052 0.4015 0.8303 0.1578 0.1918 0.2349 0.0

Remote sensing segmentation with VFM methods

status model backbone loss val_miou_present Building Mining raft Primary Forest Heavy machinery Water bodies Agricultural crop Compact mounds Gravel mounds Grass Type1 regen Type2 regen Bare ground Sluice
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) ce+dice - - - - - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) focal+dice - - - - - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) weighted_ce+dice - - - - - - - - - - - - - -
completed SAM_RS ABCNet + SAM priors seg+bdy+obj (native) 0.3104 0.1006 0.0 0.7125 0.0 0.6245 0.6795 0.1759 0.2147 0.8068 0.2614 0.1838 0.2753 0.0
completed SAM_RS CMTFNet + SAM priors seg+bdy+obj (native) 0.2909 0.2431 0.0 0.6725 0.0 0.5426 0.6788 0.0305 0.2741 0.7007 0.2317 0.1473 0.2604 0.0
completed SAM_RS FTUNetFormer + SAM priors seg+bdy+obj (native) 0.2859 0.1339 0.0 0.7817 0.0 0.4701 0.5686 0.0286 0.2696 0.8318 0.1927 0.2125 0.2271 0.0
completed SAM_RS UNetFormer + SAM priors seg+bdy+obj (native) 0.2971 0.2083 0.0 0.7157 0.0 0.4131 0.6491 0.0183 0.3926 0.8202 0.2039 0.2159 0.2254 0.0
completed RSAM-Seg SAM-ViT-B (frozen encoder) ce+dice 0.2959 0.2226 0.0 0.7836 0.0 0.662 0.3555 0.0263 0.2885 0.8042 0.2741 0.1385 0.2912 0.0
completed RSAM-Seg SAM-ViT-B (frozen encoder) focal+dice 0.2841 0.2804 0.0 0.8023 0.0 0.6016 0.4233 0.0395 0.1251 0.8108 0.2196 0.1075 0.2833 0.0
completed RSAM-Seg SAM-ViT-B (frozen encoder) weighted_ce+dice 0.3333 0.2853 0.1837 0.7512 0.0331 0.5978 0.5701 0.0385 0.402 0.7482 0.2089 0.0936 0.2681 0.152
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) ce+dice 0.2242 0.1131 0.0 0.7295 0.0 0.4984 0.201 0.0047 0.0861 0.7436 0.2142 0.1024 0.222 0.0
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) focal+dice 0.2288 0.0958 0.0017 0.7499 0.0 0.4624 0.3107 0.0161 0.0719 0.7424 0.2096 0.1025 0.2108 0.0
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) weighted_ce+dice 0.2326 0.0406 0.0308 0.7612 0.0293 0.4464 0.3085 0.0314 0.099 0.7675 0.2151 0.0861 0.2085 0.0
running SAM2.1 Hiera-B+ (full finetune, msfpn) ce+dice - - - - - - - - - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) focal+dice - - - - - - - - - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) weighted_ce+dice - - - - - - - - - - - - - -
completed SESSRS A2FPN (ce+dice) t1/t2 search + postprocess 0.3094 0.2442 0.0 0.6983 0.0 0.5238 0.6614 0.0597 0.3171 0.8411 0.2016 0.1772 0.2974 0.0
completed SESSRS A2FPN (focal) t1/t2 search + postprocess 0.3035 0.3435 0.0 0.6946 0.0 0.4638 0.5973 0.0249 0.3706 0.7669 0.2361 0.1646 0.2833 0.0
completed SESSRS A2FPN (weighted) t1/t2 search + postprocess 0.3214 0.3047 0.0704 0.6523 0.0775 0.3477 0.6681 0.1588 0.3414 0.792 0.2382 0.1579 0.2731 0.0959
completed SESSRS ABCNet (ce+dice+aux) t1/t2 search + postprocess 0.3078 0.2153 0.0 0.7418 0.0 0.5494 0.5569 0.0984 0.2907 0.8285 0.2431 0.1962 0.2809 0.0
completed SESSRS BANet (ce+dice) t1/t2 search + postprocess 0.3006 0.2044 0.0 0.752 0.0 0.5884 0.5621 0.1586 0.105 0.8109 0.2576 0.1881 0.2809 0.0
completed SESSRS MANet (ce+dice) t1/t2 search + postprocess 0.3162 0.3153 0.0 0.6773 0.0 0.6218 0.6591 0.0241 0.3258 0.8354 0.1881 0.1855 0.2779 0.0
completed SESSRS UNetFormer (ce+dice) t1/t2 search + postprocess 0.3399 0.3305 0.0 0.8089 0.0 0.5578 0.6052 0.0297 0.4677 0.8301 0.305 0.188 0.2959 0.0
completed SESSRS UNetFormer (focal) t1/t2 search + postprocess 0.3406 0.2782 0.0 0.7491 0.0 0.5993 0.7111 0.031 0.4681 0.777 0.2665 0.2483 0.2992 0.0
completed SESSRS UNetFormer (weighted) t1/t2 search + postprocess 0.3286 0.1744 0.1238 0.776 0.0 0.5211 0.68 0.068 0.4502 0.7576 0.2769 0.1504 0.293 0.0

Test

  • Source: /deac/csc/yangGrp/cuij/GoldMDD/experiments/diagnostics/test_per_class_iou_completed_models_present_only.csv
  • Heatmap: /deac/csc/yangGrp/cuij/GoldMDD/experiments/diagnostics/test_per_class_iou_completed_models_heatmap.png
  • Classes shown: 10 (GT-present in test; dropped absent classes: Heavy machinery, Compact mounds, Grass, Vehicles)
  • Running rows are placeholders (-) until eval artifacts are generated.

General segmentation methods

status model backbone loss test_miou_present Building Mining raft Primary Forest Water bodies Agricultural crop Gravel mounds Type1 regen Type2 regen Bare ground Sluice
completed DeepLabV3+ ConvNeXt-Tiny ce+dice 0.3895 0.3304 0.1906 0.7089 0.7395 0.4176 0.4109 0.298 0.2636 0.52 0.0158
completed DeepLabV3+ ConvNeXt-Tiny focal+dice 0.3735 0.4206 0.1563 0.675 0.7615 0.309 0.3516 0.294 0.2595 0.5048 0.0026
completed DeepLabV3+ ConvNeXt-Tiny weighted_ce+dice 0.3766 0.4039 0.1888 0.6503 0.7353 0.2867 0.3817 0.3098 0.2395 0.4885 0.0814
completed DeepLabV3+ ResNet-50 ce+dice 0.3662 0.4126 0.0 0.71 0.7005 0.3608 0.4825 0.2906 0.2546 0.4506 0.0
completed DeepLabV3+ ResNet-50 focal+dice 0.3515 0.3971 0.1066 0.6884 0.7172 0.2859 0.2962 0.2972 0.2549 0.4715 0.0
completed DeepLabV3+ ResNet-50 weighted_ce+dice 0.3438 0.3376 0.1955 0.6927 0.6909 0.15 0.3743 0.3336 0.24 0.423 0.0
completed UPerNet Swin-Tiny ce+dice 0.3371 0.3163 0.0689 0.6443 0.7172 0.3436 0.3114 0.3008 0.2055 0.4629 0.0
completed OCRNet HRNet-W48 ce+dice 0.2722 0.2982 0.0 0.5517 0.4619 0.1134 0.3948 0.2974 0.2469 0.3575 0.0
completed SegFormer MiT-B2 ce+dice 0.3222 0.319 0.1321 0.6619 0.5524 0.2314 0.3474 0.3223 0.2548 0.3886 0.0119
completed SegFormer MiT-B2 focal+dice 0.3332 0.3588 0.1843 0.6842 0.4357 0.3276 0.3999 0.3138 0.2634 0.357 0.0078
completed SegFormer MiT-B2 weighted_ce+dice 0.401 0.45 0.1358 0.7137 0.7636 0.3985 0.5275 0.3404 0.176 0.5043 0.0
completed Mask2Former ResNet-50 set_matching_ce+mask+dice 0.2985 0.2218 0.1155 0.7008 0.5283 0.2786 0.2635 0.2846 0.2232 0.3682 0.0
completed SegNeXt MSCAN-Tiny ce+dice 0.2682 0.3215 0.0297 0.6085 0.4882 0.0849 0.224 0.3172 0.2281 0.3802 0.0
completed Afformer AFFormer-Base ce+dice 0.3047 0.3622 0.0633 0.6749 0.4838 0.267 0.2531 0.3398 0.2436 0.3587 0.0004
completed EfficientViT-Seg EfficientViT-B2 ce+dice 0.3799 0.3306 0.0949 0.7048 0.7956 0.3461 0.475 0.3115 0.2275 0.5126 0.0
completed EfficientViT-Seg EfficientViT-B2 focal+dice 0.3693 0.3134 0.1549 0.6499 0.6826 0.3583 0.4868 0.3036 0.2498 0.4627 0.0311
completed EfficientViT-Seg EfficientViT-B2 weighted_ce+dice 0.379 0.3526 0.157 0.7041 0.7616 0.3468 0.3744 0.2903 0.2404 0.4831 0.0799
completed SeaFormer SeaFormer-Base ce+dice 0.3117 0.322 0.0141 0.685 0.4594 0.4053 0.3341 0.3299 0.2221 0.3451 0.0
completed CGRSeg EfficientFormerV2-B ce+dice 0.2679 0.3415 0.0863 0.6121 0.4065 0.1962 0.1772 0.3054 0.2107 0.3427 0.0
completed PEM ResNet-50 set_matching_ce+mask+dice 0.2789 0.1083 0.088 0.7338 0.4404 0.3529 0.2254 0.2835 0.2227 0.3336 0.0
completed RS3Mamba ResNet-18 + VMamba-Tiny ce+dice 0.2385 0.0 0.0 0.7796 0.6756 0.0 0.0 0.2615 0.2298 0.4381 0.0
completed RS3Mamba ResNet-18 + VMamba-Tiny weighted_ce+dice 0.3068 0.148 0.0 0.6587 0.5998 0.4101 0.3283 0.2975 0.2396 0.3856 0.0
completed RS3Mamba ResNet-18 + VMamba-Tiny focal+dice 0.2399 0.0 0.0 0.7723 0.6926 0.0147 0.0416 0.2654 0.1766 0.4352 0.0
completed MCPNet ResNet-50 ce (native) 0.3293 0.1945 0.0 0.7202 0.6855 0.2848 0.3914 0.3097 0.2715 0.4355 0.0
completed MCPNet ResNet-50 ce+dice 0.3056 0.1656 0.0 0.689 0.5591 0.2642 0.448 0.2901 0.2606 0.3795 0.0
completed MCPNet ResNet-50 weighted_ce+dice 0.3193 0.1766 0.1451 0.6789 0.4895 0.3776 0.3702 0.3182 0.2658 0.371 0.0
completed MCPNet ResNet-50 focal+dice 0.3233 0.1958 0.0 0.7028 0.6343 0.4144 0.3116 0.324 0.241 0.4087 0.0
completed PPMambaSeg swsl-ResNet-18 ce+dice 0.352 0.4223 0.0 0.6742 0.615 0.3353 0.5307 0.2833 0.2538 0.4057 0.0
running PPMambaSeg swsl-ResNet-18 weighted_ce+dice - - - - - - - - - - -
running PPMambaSeg swsl-ResNet-18 focal+dice - - - - - - - - - - -

Remote sensing segmentation methods

status model backbone loss test_miou_present Building Mining raft Primary Forest Water bodies Agricultural crop Gravel mounds Type1 regen Type2 regen Bare ground Sluice
completed FarSeg ResNet-50 ce (native) 0.3564 0.2997 0.0 0.6518 0.8273 0.205 0.4567 0.3081 0.2718 0.5442 0.0
completed BANet ResT-Lite ce+dice 0.2926 0.2564 0.0 0.6911 0.558 0.2844 0.2729 0.2906 0.2283 0.3438 0.0
completed ABCNet ResNet-18 ce+dice+aux_ce 0.3145 0.2693 0.0 0.6888 0.721 0.1826 0.382 0.2787 0.1956 0.4275 0.0
completed MANet ResNet-50 ce+dice 0.3711 0.5668 0.0 0.6559 0.7266 0.3445 0.4509 0.2939 0.2026 0.4702 0.0
completed MANet ResNet-50 weighted_ce+dice 0.3828 0.4335 0.2111 0.6439 0.7288 0.3581 0.4761 0.2908 0.1884 0.4531 0.0439
running MANet ResNet-50 focal+dice - - - - - - - - - - -
completed UNetFormer ResNet-18 ce+dice+aux_ce 0.3941 0.4657 0.0 0.7258 0.728 0.4635 0.5227 0.3449 0.2183 0.4723 0.0
completed UNetFormer ResNet-18 weighted_ce+dice+aux_ce 0.3566 0.3319 0.1946 0.6818 0.671 0.2865 0.4239 0.3322 0.2116 0.4327 0.0
completed UNetFormer ResNet-18 focal+dice+aux_focal 0.3765 0.4654 0.0 0.7371 0.6823 0.4142 0.474 0.336 0.2057 0.45 0.0
completed DC-Swin Swin-Small ce+dice 0.2971 0.2815 0.0 0.6661 0.6159 0.1668 0.3052 0.3172 0.24 0.3787 0.0
completed A2FPN ResNet-18 ce+dice 0.3688 0.3453 0.0 0.7085 0.8334 0.2367 0.4817 0.2882 0.2428 0.5511 0.0
completed A2FPN ResNet-18 weighted_ce+dice 0.372 0.3624 0.1482 0.7198 0.7321 0.3032 0.407 0.3043 0.2122 0.4454 0.0856
completed A2FPN ResNet-18 focal+dice 0.3363 0.3992 0.0 0.6585 0.634 0.2202 0.4728 0.315 0.2345 0.4285 0.0
completed LoGCAN ResNet-50 ce+aux_ce (native) 0.3108 0.1192 0.0 0.7278 0.8206 0.322 0.0445 0.3076 0.2489 0.5177 0.0
completed SACANet HRNet-W32 ce+aux_ce (native) 0.3294 0.336 0.0018 0.6371 0.6209 0.4379 0.2665 0.3319 0.2333 0.4283 0.0
completed FarSeg++ MiT-B2 ce (native) 0.3062 0.3413 0.1459 0.7048 0.5551 0.1487 0.2526 0.2895 0.2436 0.38 0.0
completed DOCNet HRNet-W32 ce+aux_ce (native) 0.3147 0.2662 0.0732 0.6594 0.6889 0.2644 0.2455 0.2725 0.2254 0.4512 0.0
running PyramidMamba Swin-Base ce+dice - - - - - - - - - - -
completed LoGCAN++ RepViT-M2.3 ce+aux_ce (native) 0.2264 0.0874 0.0 0.677 0.4898 0.2945 0.0581 0.1796 0.1272 0.2298 0.0
completed MF-Mamba HRNet-W18 ce+dice 0.3001 0.2849 0.0 0.657 0.5295 0.2176 0.4245 0.2855 0.2247 0.3776 0.0

Remote sensing segmentation with VFM methods

status model backbone loss test_miou_present Building Mining raft Primary Forest Water bodies Agricultural crop Gravel mounds Type1 regen Type2 regen Bare ground Sluice
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) ce+dice - - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) focal+dice - - - - - - - - - - -
running HQ-SAM ViT-B + HQ decoder (full finetune, msfpn) weighted_ce+dice - - - - - - - - - - -
completed SAM_RS ABCNet + SAM priors seg+bdy+obj (native) 0.2964 0.0928 0.0 0.6255 0.6887 0.2007 0.3997 0.3006 0.2398 0.4164 0.0
completed SAM_RS CMTFNet + SAM priors seg+bdy+obj (native) 0.2916 0.2048 0.0 0.662 0.6011 0.127 0.3726 0.2936 0.2437 0.4108 0.0
completed SAM_RS FTUNetFormer + SAM priors seg+bdy+obj (native) 0.2922 0.2637 0.0 0.7463 0.5706 0.1557 0.3117 0.271 0.2614 0.3418 0.0
completed SAM_RS UNetFormer + SAM priors seg+bdy+obj (native) 0.3241 0.2783 0.0 0.6849 0.6421 0.1958 0.4495 0.2846 0.267 0.4384 0.0
completed RSAM-Seg SAM-ViT-B (frozen encoder) ce+dice 0.3263 0.3254 0.0 0.703 0.6784 0.255 0.3121 0.3022 0.2285 0.4579 0.0
completed RSAM-Seg SAM-ViT-B (frozen encoder) focal+dice 0.345 0.324 0.0068 0.7604 0.7255 0.2763 0.3454 0.3057 0.232 0.4741 0.0
completed RSAM-Seg SAM-ViT-B (frozen encoder) weighted_ce+dice 0.3696 0.3693 0.1755 0.7118 0.697 0.3144 0.4291 0.3081 0.197 0.4374 0.0563
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) ce+dice 0.2422 0.2552 0.0441 0.6777 0.4286 0.0149 0.2028 0.306 0.1635 0.3288 0.0
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) focal+dice 0.2351 0.2074 0.0479 0.696 0.3906 0.0482 0.1868 0.2984 0.1556 0.3204 0.0
completed SAM2.1 Hiera-B+ (frozen backbone, msfpn) weighted_ce+dice 0.2207 0.0778 0.0403 0.685 0.3653 0.0532 0.2506 0.2871 0.1351 0.3102 0.0027
running SAM2.1 Hiera-B+ (full finetune, msfpn) ce+dice - - - - - - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) focal+dice - - - - - - - - - - -
running SAM2.1 Hiera-B+ (full finetune, msfpn) weighted_ce+dice - - - - - - - - - - -
completed SESSRS A2FPN (ce+dice) t1/t2 search + postprocess 0.3702 0.3508 0.0 0.7085 0.8338 0.2368 0.489 0.2883 0.243 0.5519 0.0
completed SESSRS A2FPN (focal) t1/t2 search + postprocess 0.3374 0.4018 0.0 0.6584 0.6353 0.2203 0.4785 0.3156 0.2347 0.4292 0.0
completed SESSRS A2FPN (weighted) t1/t2 search + postprocess 0.3745 0.3669 0.1513 0.7198 0.7334 0.3035 0.4118 0.3048 0.2127 0.4463 0.0943
completed SESSRS ABCNet (ce+dice+aux) t1/t2 search + postprocess 0.3154 0.272 0.0 0.6887 0.7224 0.1825 0.3858 0.2794 0.1958 0.4277 0.0
completed SESSRS BANet (ce+dice) t1/t2 search + postprocess 0.2937 0.2585 0.0 0.6911 0.5584 0.2844 0.2812 0.2907 0.2286 0.3438 0.0
completed SESSRS MANet (ce+dice) t1/t2 search + postprocess 0.3604 0.5642 0.0 0.6667 0.6537 0.2792 0.4624 0.3063 0.1918 0.48 0.0
completed SESSRS UNetFormer (ce+dice) t1/t2 search + postprocess 0.3958 0.4708 0.0 0.7259 0.7281 0.4633 0.5327 0.3453 0.2184 0.4735 0.0
completed SESSRS UNetFormer (focal) t1/t2 search + postprocess 0.3873 0.4662 0.0 0.7098 0.7649 0.385 0.4858 0.3149 0.2631 0.4838 0.0
completed SESSRS UNetFormer (weighted) t1/t2 search + postprocess 0.3578 0.3334 0.1955 0.6817 0.6728 0.2858 0.4299 0.333 0.2123 0.4335 0.0