AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion

Tuan-Anh Vu, Duc Thanh Nguyen, Qing Guo, Nhat Minh Chung, Binh‐Son Hua, Ivor Wai-Hung Tsang, Sai-Kit Yeung

IJCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 9 citations (OpenAlex)

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
fine-tune on COD10K-v3 training setOurs · COD10K-v3 testAP: 23.9 -> 45.1Improved
fine-tune on COD10K-v3 training setOurs · NC4KAP: 24.8 -> 52.9Improved
add text embeddings (vs zero text embeddings) (ablation)Ours · COD10K-v3 testAP: -7.1 (19.3 vs 12.2)Improved
add text embeddings (vs zero) after task-specific fine-tuning (ablation)Ours (task-specific) · COD10K-v3 testAP: 44.9 vs 31.4 (-13.5)Improved
add MSFF multi-scale fusion over all U-Net layers (vs last layer only) (ablation)Ours · COD10K-v3 testAP: -0.9 (18.4 vs 19.3)Improved
add MSFF fusion (vs concatenation of all multiscale features) (ablation)Ours · COD10K-v3 testAP: -1.2 (18.1 vs 19.3)Improved
add CIN module (ablation)Ours · COD10K-v3 testAP: 19.3 -> from 17.6 without itImproved
add TVA module (vs element-wise dot product) (ablation)Ours · COD10K-v3 testAP: -0.5 (18.8 vs 19.3)Improved
add prompt engineering (synonyms, plurals ensemble) (ablation)Ours · COD10K-v3 testAP: 22.8 -> 23.4Improved
add multiple camouflage-specific prompt templates (ablation)Ours · COD10K-v3 testAP: 23.4 -> 23.9Improved
replace fine-grained class names with coarser hypernym prompts (ablation)Ours · COD10K-v3 testAP: 23.9 -> 22.7Hurt
replace fine-grained class names with coarser hypernym prompts (ablation)Ours · NC4KAP: 24.8 -> 23.6Hurt

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.

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