efficient-probing-heads / manifest.json
billpsomas's picture
Link the paper page; SigLIP2 SO400M head is now the best epoch (13 peak heads)
297878d verified
Raw
History Blame Contribute Delete
25.9 kB
{
"heads": [
{
"method": "MAE",
"arch": "ViT-S/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_small_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_small_patch16_224.mae/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 64.56,
"table_best_acc1": 64.58,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/mae_vits/ep.txt",
"params_incl_bn_stats": 545513,
"file": "mae_vits/ep_head.pth",
"size_mb": 2.2
},
{
"method": "MAE",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.mae",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 86,
"val_acc1_at_head_epoch": 75.35,
"table_best_acc1": 75.46,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/mae_base/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "mae_base/ep_head.pth",
"size_mb": 5.5
},
{
"method": "MAE",
"arch": "ViT-L/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_large_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_large_patch16_224.mae",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 79.43,
"table_best_acc1": 79.52,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/mae_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "mae_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "BEiTv2",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "simmim",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.beitv2/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 81.32,
"table_best_acc1": 81.39,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/beitv2_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "beitv2_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "SimMIM",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "simmim",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.simmim/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 64.81,
"table_best_acc1": 64.86,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/simmim_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "simmim_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "CAPI",
"arch": "ViT-L/14",
"pretrain": "IN-1K",
"image_size": 224,
"model": "capi_vitl14_in1k",
"loader": "capi",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 82.43,
"table_best_acc1": 82.98,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/capi_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "capi_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "DINO",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.dino",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 77.08,
"table_best_acc1": 77.39,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/dino_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "dino_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "iBOT",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.ibot/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 78.62,
"table_best_acc1": 78.98,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/ibot_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "ibot_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "DINOv2",
"arch": "ViT-B/14",
"pretrain": "LVD-142M",
"image_size": 224,
"model": "dinov2_vitb14",
"loader": "hub",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 25,
"val_acc1_at_head_epoch": 83.61,
"table_best_acc1": 84.01,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/dinov2_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "dinov2_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "DINOv2",
"arch": "ViT-L/14",
"pretrain": "LVD-142M",
"image_size": 224,
"model": "dinov2_vitl14",
"loader": "hub",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 15,
"val_acc1_at_head_epoch": 85.56,
"table_best_acc1": 85.56,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/dinov2_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "dinov2_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "DINOv3",
"arch": "ViT-B/16",
"pretrain": "LVD-1689M",
"image_size": 224,
"model": "dinov3_vitb16",
"loader": "dinov3",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 20,
"val_acc1_at_head_epoch": 83.77,
"table_best_acc1": 84.11,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/dinov3_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "dinov3_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "DINOv3",
"arch": "ViT-L/16",
"pretrain": "LVD-1689M",
"image_size": 224,
"model": "dinov3_vitl16",
"loader": "dinov3",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 19,
"val_acc1_at_head_epoch": 86.73,
"table_best_acc1": 87.05,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/dinov3_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "dinov3_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "CLIP",
"arch": "ViT-L/14",
"pretrain": "WIT-400M",
"image_size": 224,
"model": "ViT-L-14",
"loader": "openclip",
"pretrain_tag": "openai",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 11,
"val_acc1_at_head_epoch": 83.22,
"table_best_acc1": 83.22,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/clip_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "clip_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "SigLIP",
"arch": "ViT-L/16",
"pretrain": "WebLI (10B imgs, 109 langs)",
"image_size": 256,
"model": "ViT-L-16-SigLIP-256",
"loader": "openclip",
"pretrain_tag": "webli",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 85.93,
"table_best_acc1": 85.93,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/siglip_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "siglip_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "SigLIP2",
"arch": "ViT-L/16",
"pretrain": "WebLI (10B imgs, 109 langs)",
"image_size": 256,
"model": "ViT-L-16-SigLIP2-256",
"loader": "openclip",
"pretrain_tag": "webli",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 87.06,
"table_best_acc1": 87.06,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/siglip2_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "siglip2_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "DiT",
"arch": "DiT-XL/2",
"pretrain": "IN-1K",
"image_size": 256,
"model": "DiT-XL/2",
"loader": "dit",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 128,
"d_out": 1,
"head_epoch": 86,
"val_acc1_at_head_epoch": 56.94,
"table_best_acc1": 57.0,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/dit_xl/ep.txt",
"params_incl_bn_stats": 2629865,
"file": "dit_xl/ep_head.pth",
"size_mb": 10.5
},
{
"method": "AIMv2",
"arch": "ViT-L/14",
"pretrain": "DFN-2B + COYO + HQITP",
"image_size": 224,
"model": "aimv2-large-patch14-224",
"loader": "aimv2",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 19,
"val_acc1_at_head_epoch": 85.62,
"table_best_acc1": 85.94,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/aimv2_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "aimv2_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "SigLIP2",
"arch": "SO400M/14",
"pretrain": "WebLI (10B imgs, 109 langs)",
"image_size": 224,
"model": "ViT-SO400M-14-SigLIP2",
"loader": "openclip",
"pretrain_tag": "webli",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 87.68,
"table_best_acc1": 87.68,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/siglip2_so400m/ep.txt",
"params_incl_bn_stats": 2519273,
"file": "siglip2_so400m/ep_head.pth",
"size_mb": 10.1
},
{
"method": "EVA02",
"arch": "ViT-L/14",
"pretrain": "IN-22K",
"image_size": 224,
"model": "eva02_large_patch14_224.mim_in22k",
"loader": "timm",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 83.22,
"table_best_acc1": 83.58,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/eva02_vitl_mim/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "eva02_vitl_mim/ep_head.pth",
"size_mb": 8.4
},
{
"method": "RADIO",
"arch": "ViT-L/16",
"pretrain": "distilled (DFN5B/SigLIP/DINOv2/SAM)",
"image_size": 224,
"model": "radio_v2.5-l",
"loader": "radio",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 83.4,
"table_best_acc1": 83.89,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/radio_v25_l/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "radio_v25_l/ep_head.pth",
"size_mb": 8.4
},
{
"method": "Hiera",
"arch": "ViT-H/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "hiera_huge_224.mae",
"loader": "timm",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 79.82,
"table_best_acc1": 79.89,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/hiera_huge/ep.txt",
"params_incl_bn_stats": 6312937,
"file": "hiera_huge/ep_head.pth",
"size_mb": 25.3
},
{
"method": "Hiera",
"arch": "ViT-L/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "hiera_large_224.mae",
"loader": "timm",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 83,
"val_acc1_at_head_epoch": 78.51,
"table_best_acc1": 78.55,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/hiera_large/ep.txt",
"params_incl_bn_stats": 2519273,
"file": "hiera_large/ep_head.pth",
"size_mb": 10.1
},
{
"method": "Hiera",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "hiera_base_224.mae",
"loader": "timm",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 88,
"val_acc1_at_head_epoch": 75.63,
"table_best_acc1": 75.68,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/hiera_base/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "hiera_base/ep_head.pth",
"size_mb": 5.5
},
{
"method": "RADIO",
"arch": "ViT-B/16",
"pretrain": "distilled (DFN5B/SigLIP/DINOv2/SAM)",
"image_size": 224,
"model": "radio_v2.5-b",
"loader": "radio",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 80.26,
"table_best_acc1": 80.29,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/radio_v25_b/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "radio_v25_b/ep_head.pth",
"size_mb": 5.5
},
{
"method": "CLIP",
"arch": "ViT-B/16",
"pretrain": "WIT-400M",
"image_size": 224,
"model": "ViT-B-16",
"loader": "openclip",
"pretrain_tag": "openai",
"finetune": "",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 11,
"val_acc1_at_head_epoch": 77.85,
"table_best_acc1": 77.85,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/clip_vitb16/ep.txt",
"params_incl_bn_stats": 792553,
"file": "clip_vitb16/ep_head.pth",
"size_mb": 3.2
},
{
"method": "PE-Core",
"arch": "L-14/336",
"pretrain": "MetaCLIP-curated 5.4B",
"image_size": 336,
"model": "PE-Core-L-14-336",
"loader": "openclip",
"pretrain_tag": "meta",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 12,
"val_acc1_at_head_epoch": 87.25,
"table_best_acc1": 87.25,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/pe_core_l336/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "pe_core_l336/ep_head.pth",
"size_mb": 8.4
},
{
"method": "EVA02-CLIP",
"arch": "E-14",
"pretrain": "LAION-2B (4B seen)",
"image_size": 224,
"model": "EVA02-E-14",
"loader": "openclip",
"pretrain_tag": "laion2b_s4b_b115k",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 87.7,
"table_best_acc1": 87.7,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/eva02_e14/ep.txt",
"params_incl_bn_stats": 5065193,
"file": "eva02_e14/ep_head.pth",
"size_mb": 20.3
},
{
"method": "MetaCLIP2",
"arch": "ViT-bigG/14",
"pretrain": "MetaCLIP2-worldwide (300+ langs)",
"image_size": 224,
"model": "ViT-bigG-14-worldwide",
"loader": "openclip",
"pretrain_tag": "metaclip2_worldwide",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 87.11,
"table_best_acc1": 87.11,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/metaclip2_bigg/ep.txt",
"params_incl_bn_stats": 4490473,
"file": "metaclip2_bigg/ep_head.pth",
"size_mb": 18.0
},
{
"method": "DINOv3",
"arch": "ViT-7B/16",
"pretrain": "LVD-1689M",
"image_size": 224,
"model": "dinov3_vit7b16",
"loader": "dinov3",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 88.36,
"table_best_acc1": 88.36,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/dinov3_vit7b/ep.txt",
"params_incl_bn_stats": 21013481,
"file": "dinov3_vit7b/ep_head.pth",
"size_mb": 84.1
},
{
"method": "MaskFeat",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.maskfeat/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 71.68,
"table_best_acc1": 71.76,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/maskfeat_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "maskfeat_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "I-JEPA",
"arch": "ViT-H/14",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_huge_patch14",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_huge_patch14_224.ijepa/checkpoint-799.pth",
"extra_flags": "--no_cls_token",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 78.8,
"table_best_acc1": 79.0,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/ijepa_vith/ep.txt",
"params_incl_bn_stats": 2962921,
"file": "ijepa_vith/ep_head.pth",
"size_mb": 11.9
},
{
"method": "MoCov3",
"arch": "ViT-B/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_base_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_base_patch16_224.mocov3/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 76.21,
"table_best_acc1": 76.53,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/mocov3_vitb/ep.txt",
"params_incl_bn_stats": 1384937,
"file": "mocov3_vitb/ep_head.pth",
"size_mb": 5.5
},
{
"method": "iBOT",
"arch": "ViT-L/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_large_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_large_patch16_224.ibot/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 79.43,
"table_best_acc1": 79.97,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/ibot_vitl/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "ibot_vitl/ep_head.pth",
"size_mb": 8.4
},
{
"method": "MetaCLIP2",
"arch": "ViT-bigG/14-378",
"pretrain": "MetaCLIP2-worldwide (300+ langs)",
"image_size": 378,
"model": "ViT-bigG-14-worldwide-378",
"loader": "openclip",
"pretrain_tag": "metaclip2_worldwide",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 88.12,
"table_best_acc1": 88.12,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/metaclip2_bigg378/ep.txt",
"params_incl_bn_stats": 4490473,
"file": "metaclip2_bigg378/ep_head.pth",
"size_mb": 18.0
},
{
"method": "MaskFeat",
"arch": "ViT-L/16",
"pretrain": "IN-1K",
"image_size": 224,
"model": "vit_large_patch16",
"loader": "",
"pretrain_tag": "",
"finetune": "vit_large_patch16_224.maskfeat/checkpoint-799.pth",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 89,
"val_acc1_at_head_epoch": 69.56,
"table_best_acc1": 69.63,
"note": "final-epoch head, not best-epoch: checkpoints overwrite per epoch. table_best_acc1 is the peak of the same run; the difference is the post-peak decline of a frozen-feature probe, largest on VLM encoders.",
"training_log": "logs/maskfeat_large/ep.txt",
"params_incl_bn_stats": 2108393,
"file": "maskfeat_large/ep_head.pth",
"size_mb": 8.4
},
{
"method": "EVA02-CLIP",
"arch": "E-14-plus",
"pretrain": "LAION-2B (9B seen)",
"image_size": 224,
"model": "EVA02-E-14-plus",
"loader": "openclip",
"pretrain_tag": "laion2b_s9b_b144k",
"finetune": "",
"extra_flags": "",
"cls_features": "ep",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 6,
"val_acc1_at_head_epoch": 87.98,
"table_best_acc1": 87.98,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/eva02_e14_plus/ep.txt",
"params_incl_bn_stats": 5065193,
"file": "eva02_e14_plus/ep_head.pth",
"size_mb": 20.3
},
{
"method": "Franca",
"arch": "ViT-L/14",
"pretrain": "LAION-600M",
"image_size": 224,
"model": "franca_vitl14",
"loader": "franca",
"pretrain_tag": "",
"finetune": "",
"extra_flags": "--franca_weights LAION",
"cls_features": "ep_all",
"ep_queries": 32,
"d_out": 1,
"head_epoch": 14,
"val_acc1_at_head_epoch": 84.28,
"table_best_acc1": 84.28,
"note": "best-epoch head: saved at the run's peak, the number the table reports.",
"training_log": "logs/franca_laion/ep_all.txt",
"params_incl_bn_stats": 2108393,
"file": "franca_laion/ep_head.pth",
"size_mb": 8.4
}
],
"missing": []
}