| --- |
| license: apache-2.0 |
| tags: |
| - image-text-retrieval |
| - jepa |
| - contrastive-learning |
| - video-encoder |
| - pytorch |
| pipeline_tag: feature-extraction |
| --- |
| |
| # scout-eccv-x-explora |
|
|
| Part of **SCOUT** (Sim-to-real Contrastive Outlier Understanding via Text), an ECCV 2026 workshop |
| paper on JEPA-based text-based person re-identification for the AI City Challenge Track 4 (Sim2Real). |
| Code: https://github.com/abtraore/SCOUT-ECCV |
|
|
| The paper's best single-model result: y-clip-v17 recipe + ExPLoRA-adapted X-encoder (partial block unfreeze + LoRA r=32 on the frozen V-JEPA2 ViT-L/16, selected via an Auto-RGN sensitivity probe) on top of a frozen CLIP-ViT-L/14 text tower. |
|
|
| - **Val mAP@10**: 0.9297 |
| - **Val Hit@10**: 0.9948 |
| - **Trainable / total parameters**: 635.4M / 1291.3M |
|
|
| RECOMMENDED default checkpoint. The only run in the paper that trains the X-encoder; a precision (R@1) gain that transferred to a board-champion result inside the full fusion system. |
|
|
| ## What's in this repo |
|
|
| Only the parameters SCOUT actually trained: a `model.safetensors` (trainable predictor weights, and |
| for ExPLoRA/LoRA variants, the adapted encoder deltas) plus a `config.json` recording the exact recipe. |
| Frozen backbone weights (V-JEPA2 from Meta, the text encoder from its own source) are **not** included |
| here; they're downloaded from their own public sources at load time. |
|
|
| ## Usage |
|
|
| ```python |
| from scripts.load_from_hf import load_from_hf |
| |
| model = load_from_hf("Abdrah/scout-eccv-x-explora").eval() |
| # model.encode_image(pixel_values) # [B, 3, 384, 384] in [0, 1] -> [B, out_dim] L2-normalized |
| # model.encode_text(["a caption"]) # -> [B, out_dim] L2-normalized |
| ``` |
|
|
| Or drop it straight into the repo's own evaluation script: |
|
|
| ```bash |
| uv run python scripts/local_eval.py --hf-repo Abdrah/scout-eccv-x-explora --pab-root /path/to/PAB --query-source val |
| ``` |
|
|
| ## License |
|
|
| Apache 2.0 (see the source repo's LICENSE/NOTICE). This checkpoint does not redistribute any frozen |
| backbone weights, which carry their own upstream licenses. |
|
|
