Research map / Detection and segmentation / CNN features
CODiff: One-Step Diffusion Model for Camouflaged Object Detection
Xiaotong Fu, Qian Liu, Qihang Zhou, Wenchao Meng, Qinmin Yang, Shibo He
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add global <cls> token and timestep embedding guidance (GSG) to the denoiser (ablation) | CODiff · COD10K | weighted F-measure: 0.838 -> 0.852 | Improved |
| add timestep embedding alongside <cls> token (ablation) | CODiff · NC4K | MAE: 0.021 -> 0.020 | No clear effect |
| use multi-level DINOv2 features [3,6,9,12] instead of only final layer in HCI (ablation) | CODiff · COD10K | weighted F-measure: 0.803 -> 0.852 | Improved |
| add a fourth DINOv2 layer (layer 3) beyond [6,9,12] (ablation) | CODiff · NC4K | S-alpha: 0.911 -> 0.911 | No clear effect |
| add representation alignment loss LRA with lambda 0.75 (ablation) | CODiff · COD10K | MAE: 0.017 -> 0.014 | Improved |
| raise LRA weight from 0.75 to 1.0 (ablation) | CODiff · COD10K | S-alpha: 0.896 -> 0.890 | Hurt |
| replace PVTv2 trainable encoder with frozen DINOv2 in a prior diffusion COD model (ablation) | CamoDiffusion · COD10K | S-alpha: 0.880 -> 0.870 | Hurt |
| use CODiff framework instead of CamoDiffusion with the same frozen DINOv2 backbone (ablation) | frozen DINOv2 · COD10K | S-alpha: 0.870 -> 0.896 | Improved |
| use one-step sampling instead of 10-step sampling | diffusion-based COD · COD10K | sampling time (s/img): 0.18 -> 0.07 | Improved |
| one-step CODiff versus the strongest transformer method ZoomNeXt-P on COD10K S-alpha | CODiff · COD10K | S-alpha: 0.898 -> 0.896 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CamoDiffusion — CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models (AAAI 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models (AAAI 2024 · similarity 0.95)
- Conditional Diffusion Models for Camouflaged and Salient Object Detection (TPAMI 2025 · similarity 0.94)
- DiffusionDet: Diffusion Model for Object Detection (ICCV 2023 · similarity 0.91)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.87)
- Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection (CVPR 2025 · similarity 0.87)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
