AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detection

Huafeng Chen, Chenguang Zhu, Yueming Lyu, Caifeng Shan

CVPR 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection

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 changedWhereMeasuredEffect
add CA-CoT prompting to MLLM+SAM teacher (ablation)MLLM + SAM teacher · COD10KMAE: 0.232 -> 0.085Improved
add Graded Mask Evaluator to filter low-quality masks (ablation)UCOD-MKD with CA-CoT · COD10KMAE: 0.085 -> 0.041Improved
add GKD distillation (ablation)UCOD-MKD · COD10KMAE: 0.041 -> 0.031Improved
add each CA-CoT reasoning step (STEP1 to STEP4) (ablation)CA-CoT · COD10KMAE: 0.232 -> 0.085Improved
add SIM-based mask grading in GME (ablation)GME baseline · COD10KMAE: 0.085 -> 0.066Improved
add both FGC and ETC to SIM (ablation)GME · COD10KMAE: 0.066 -> 0.041Improved
use SSIM together with IoU in SIM (ablation)GME SIM · COD10KMAE: 0.071 -> 0.066Improved
add pixel-level enhancement (S and M) (ablation)GKD · COD10KMAE: 0.041 -> 0.038Improved
add L1 and MSE losses for high-quality samples (ablation)GKD image-level enhancement · COD10KMAE: 0.041 -> 0.035Improved
add low-quality samples to training (ablation)COD distillation · CAMO+COD10K trainingE-measureHurt
use fewer high-quality samples instead of more random samples (ablation)COD distillation · E-measure vs training samplesE-measureImproved
replace DINO backbone dependence with MLLM+SAM supervisionUCOD-MKD vs UCOD-DPL · COD10KMAE: 0.059 -> 0.031Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy