Initial upload

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model:
+- openai/clip-vit-base-patch16
+- openai/clip-vit-base-patch32
+pipeline_tag: zero-shot-image-classification
+tags:
+- clip
+- vision-language
+- prompt-learning
+- contrastive-learning
+- distribution-shift
+---
+
+# ReCalCon
+
+Checkpoints for **Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language
+Models** (BMVC 2026). [Paper](https://arxiv.org/abs/2609.06967) · [Code](https://github.com/SoongE/ReCalCon)
+
+Each folder holds `model.safetensors` (the full model state dict, fp32) and `config.json`, which names the released
+config to evaluate it with.
+
+## Usage
+
+```bash
+hf download SoongE/ReCalCon --include "distribution_shift/imagenet_b16/*" --local-dir checkpoints
+python -m scripts.eval --config imagenet_b16 \
+  --eval.checkpoint checkpoints/distribution_shift/imagenet_b16/model.safetensors
+```
+
+## Checkpoints
+
+**Distribution shift** (top-1 accuracy, %)
+
+| Checkpoint | Row | ImageNet | -R | -A | -V2 | -Sketch | ObjectNet |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| `distribution_shift/imagenet_b16` | ViT-B/16, Update, ImageNet | 83.284 | 71.607 | 54.893 | 74.1 | 51.781 | 58.388 |
+| `distribution_shift/imagenet_b32` | ViT-B/32, Update, ImageNet | 79.354 | 62.41 | 32.573 | 68.15 | 44.503 | 49.203 |
+| `distribution_shift/imagenet_petl_b16` | ViT-B/16, Freeze (PETL), ImageNet | 80.206 | 73.163 | 50.867 | 70.13 | 49.614 | 55.691 |
+| `distribution_shift/imagenet_petl_b32` | ViT-B/32, Freeze (PETL), ImageNet | 76.12 | 63.563 | 30.453 | 64.52 | 42.267 | 46.662 |
+
+iWildCam (macro-F1, %). The released evaluation reports the OOD split.
+
+| Checkpoint | Row | ID (macro-F1) | OOD (macro-F1) |
+| --- | --- | --- | --- |
+| `distribution_shift/iwildcam_b16` | ViT-B/16, Update, iWildCam | 51.253 | 37.803 |
+| `distribution_shift/iwildcam_b32` | ViT-B/32, Update, iWildCam | 42.116 | 29.275 |
+| `distribution_shift/iwildcam_petl_b16` | ViT-B/16, Freeze (PETL), iWildCam | 45.49 | 30.327 |
+| `distribution_shift/iwildcam_petl_b32` | ViT-B/32, Freeze (PETL), iWildCam | 34.709 | 24.502 |
+
+**Transfer learning** (top-1 accuracy, %)
+
+| Checkpoint | Dataset | Accuracy |
+| --- | --- | --- |
+| `transfer/caltech101` | Caltech101 | 97.85 |
+| `transfer/flowers102` | Flowers102 | 98.894 |
+| `transfer/pcam` | PCam | 89.413 |
+| `transfer/stanfordcars` | StanfordCars | 91.419 |
+
+## License
+
+Apache License 2.0. The models are fine-tuned from OpenAI CLIP (MIT License); each evaluation dataset keeps its own
+terms.
+
+## Citation
+
+```bibtex
+@inproceedings{oh2026recalibrated,
+  title     = {Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models},
+  author    = {Oh, Seungmin and Kang, Seunghun and Ryu, Jongbin},
+  booktitle = {Proceedings of the British Machine Vision Conference},
+  year      = {2026},
+  publisher = {BMVA},
+  url       = {https://arxiv.org/abs/2609.06967}
+}
+```

distribution_shift/imagenet_b16/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "imagenet_b16"
+}

distribution_shift/imagenet_b16/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809660e5076c1c3a37d0f0e0f7b8f005789ba1dcb4e93da69d8470ac31917bbd
+size 615332308

distribution_shift/imagenet_b32/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "imagenet_b32"
+}

distribution_shift/imagenet_b32/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414e73f903249d20d36275a4c856226698e28827e989eb72fda2d4571b4a66b5
+size 621958612

distribution_shift/imagenet_petl_b16/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "imagenet_petl_b16"
+}

distribution_shift/imagenet_petl_b16/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651284eb228862b6147d544c3b8302deceeb03c0ceff6317495af82def5363d8
+size 615332308

distribution_shift/imagenet_petl_b32/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "imagenet_petl_b32"
+}

distribution_shift/imagenet_petl_b32/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7be0aba87cf5c3baf86e4dcbf39699e9d9c037c2bbadb085b2f3fbf4c39e95
+size 621958612

distribution_shift/iwildcam_b16/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "iwildcam_b16"
+}

distribution_shift/iwildcam_b16/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac910d11f5c68e19e33ff721fd39cb48a45556de7033b17446716ccc44d5779
+size 615332308

distribution_shift/iwildcam_b32/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "iwildcam_b32"
+}

distribution_shift/iwildcam_b32/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da01920c19eba317317bfa7a1977f50ef26d25b1e98c07d12aab163842a1d87
+size 621958612

distribution_shift/iwildcam_petl_b16/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "iwildcam_petl_b16"
+}

distribution_shift/iwildcam_petl_b16/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d38c8b6cb8fda394b5cd33a7befbbb0b0c087c841b1211405a1cac6e68920c4
+size 615332308

distribution_shift/iwildcam_petl_b32/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "iwildcam_petl_b32"
+}

distribution_shift/iwildcam_petl_b32/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff3113bacba5e1b34aa8c6f1bd30278047b15fbda6eca520b72cc75906a6a81
+size 621958612

transfer/caltech101/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "transfer_caltech101"
+}

transfer/caltech101/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25398bb69e7b057fbd4ef9136371090725e86a07966f73f87576a16399fcd678
+size 615332308

transfer/flowers102/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "transfer_flowers102"
+}

transfer/flowers102/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab67c99558bd5d7df1e160f32a03324599f2ea3ccd0ad6e2941a3349d99364bb
+size 615332308

transfer/pcam/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "transfer_pcam"
+}

transfer/pcam/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c49d7896cc8e053e262ab2a90312927dfab796a7913ffb81e692946559c281a
+size 615332308

transfer/stanfordcars/config.json

@@ -0,0 +1,3 @@
+{
+  "config": "transfer_stanfordcars"
+}

transfer/stanfordcars/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0da0bf1f637747bc5a145ba25379b3b3dc6ba3f3e6166961a58a394cca2733
+size 615332308