Hugging Face's logo

MikelWL
/
icar-weights

OpenCLIP
image-text-retrieval
retrieval
openclip
vit
icar
Model card Files
xet
Community
icar-weights / README.md
MikelWL's picture
MikelWL
Upload README.md with huggingface_hub
0d26d84 verified
preview code
|
raw
history blame contribute delete
2.42 kB
metadata
license: mit
library_name: open_clip
tags:
  - image-text-retrieval
  - retrieval
  - openclip
  - vit
  - icar

ICAR Weights (OpenCLIP ViT-L-14, LAION-2B)

This repository provides ICAR fine-tuned OpenCLIP ViT-L-14 (LAION-2B) weights, including early-exit variants, used in the paper "Image Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models".

Paper: https://arxiv.org/abs/2512.15372 Code: https://github.com/MikelWL/ICAR

These weights are intended to be used with the ICAR codebase. The standard retrieval setting reported in the paper evaluates COCO/Flickr test queries against a gallery augmented with 100k LAION-COCO distractors.

Contents

All weights are stored under the checkpoints/ directory to match the ICAR codebase layout.

Baselines (full path)

  • checkpoints/baseline_coco/latest_checkpoint.pt
  • checkpoints/baseline_flickr/latest_checkpoint.pt

Early-exit variants (ICAR)

  • checkpoints/icar_coco/layer_8/latest_checkpoint.pt
  • checkpoints/icar_coco/layer_12/latest_checkpoint.pt
  • checkpoints/icar_coco/layer_16/latest_checkpoint.pt
  • checkpoints/icar_coco/layer_20/latest_checkpoint.pt
  • checkpoints/icar_flickr/layer_8/latest_checkpoint.pt
  • checkpoints/icar_flickr/layer_12/latest_checkpoint.pt
  • checkpoints/icar_flickr/layer_16/latest_checkpoint.pt
  • checkpoints/icar_flickr/layer_20/latest_checkpoint.pt

Usage

Use the ICAR scripts as the primary entrypoints. See the main repo README for reference scripts and required data paths.

Example (mixed evaluation):

python scripts/evaluate_mixed_preprocessed.py \
  --config icar/configs/coco.yaml \
  --checkpoint checkpoints/icar_coco/layer_12/latest_checkpoint.pt \
  --base-dataset mscoco \
  --base-data-root /path/to/coco-images \
  --laion-data-root /path/to/laion_coco_100k \
  --complexity-scores /path/to/laion_coco_100k_metadata/complexity_scores.json \
  --early-exit-layer 12 \
  --use-icc-routing \
  --icc-checkpoint /path/to/icc_weights.pt \
  --eval-category

ICC Weights

ICC (Image Complexity Classifier) weights are hosted separately due to non-commercial licensing restrictions on the ImageNet-pretrained ConvNeXt-V2 checkpoint. Please download ICC weights from the dedicated ICC repository.

License

The ICAR weights in this repository follow the OpenCLIP license (MIT). See the OpenCLIP repository for details and attribution requirements.