---
license: apache-2.0
base_model: cfcamo/cfcamo-sft-4b
pipeline_tag: image-text-to-text
library_name: peft
language:
  - en
tags:
  - vision-language
  - camouflaged-object-detection
  - reinforcement-learning
  - lora
  - peft
  - qwen3-vl
---

# CFCamo-4B (RL-LoRA adapter)

LoRA adapter for **CFCamo**: trained on top of
[cfcamo/cfcamo-sft-4b](https://huggingface.co/cfcamo/cfcamo-sft-4b) with
**Counterfactual Sequence Policy Optimization (CSPO)** and a **Counterfactual
Paired Reward (CPR)**. This is the paper LoRA checkpoint at step 252 (ε=0.5)
over the 4040-pair RL set — the single-large-GPU alternative to
[cfcamo/cfcamo-rl-full](https://huggingface.co/cfcamo/cfcamo-rl-full).

- 📄 Paper: <https://arxiv.org/abs/2606.11231>
- Code & training recipe: <https://github.com/suhang2000/CFCamo>
- Benchmark (CF-COD) + training data: <https://huggingface.co/datasets/cfcamo/CF-COD>

## Use it (PEFT load)

```python
from transformers import AutoModelForImageTextToText, AutoProcessor
from peft import PeftModel

base   = AutoModelForImageTextToText.from_pretrained(
    "cfcamo/cfcamo-sft-4b", torch_dtype="auto", device_map="auto",
).eval()
model  = PeftModel.from_pretrained(base, "cfcamo/cfcamo-rl-lora").eval()
processor = AutoProcessor.from_pretrained("cfcamo/cfcamo-sft-4b")
# (use the same detect-or-abstain prompt as cfcamo-rl-full — see that model card)
```

Or merge into a single standalone HF model:

```bash
python scripts/eval/merge_lora.py \
  --base checkpoints/cfcamo-sft-4b \
  --lora checkpoints/cfcamo-rl-lora \
  --out checkpoints/cfcamo-rl-lora-merged
```

## Reproduce paper LoRA numbers

```bash
git clone https://github.com/suhang2000/CFCamo && cd CFCamo
pip install -e ".[eval]"
huggingface-cli download cfcamo/cfcamo-sft-4b --local-dir checkpoints/cfcamo-sft-4b
huggingface-cli download cfcamo/cfcamo-rl-lora --local-dir checkpoints/cfcamo-rl-lora
huggingface-cli download --repo-type dataset cfcamo/CF-COD --local-dir data/cfcod
# (place upstream COD into data/cfcod/<source>/{Imgs,GT}/ — see dataset card)

python scripts/eval/merge_lora.py \
  --base checkpoints/cfcamo-sft-4b \
  --lora checkpoints/cfcamo-rl-lora \
  --out checkpoints/cfcamo-rl-lora-merged

python scripts/eval/eval_cfcod.py \
  --cf-manifest data/cfcod/test/cf_manifest_test.jsonl \
  --data-root data/cfcod \
  --models "CFCamo-LoRA=checkpoints/cfcamo-rl-lora-merged" \
  --out-dir results/cfcod_eval
```

## Training summary

- Base: cfcamo/cfcamo-sft-4b (SFT cold-start on Qwen3-VL-4B-Instruct)
- RL: CSPO/CPR (eta=1.0), LoRA r=64, single large GPU
- Checkpoint at step 252 = ε=0.5 over the 4040-pair RL set

## Citation

```bibtex
@article{li2026cfcamo,
  title   = {{CFCamo}: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection},
  author  = {Li, Suhang and Yoshie, Osamu and Ieiri, Yuya},
  journal = {arXiv preprint arXiv:2606.11231},
  year    = {2026}
}
```