AI Paper Atlas

Research map / Detection and segmentation / CNN features

Enhancing Prompt Generation with Adaptive Refinement for Camouflaged Object Detection

Xuehan Chen, Guangyu Ren, Tianhong Dai, Tania Stathaki, Hengyan Liu

ICCV 2025 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 2 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
add auxiliary sparse embedding (BLIP noun + image embedding) (ablation)SAM · COD10KS-measure: 0.810 -> 0.820Improved
add auxiliary sparse embedding (ablation)SAM · CHAMELEONmax F-measure: 0.820 -> 0.816Hurt
add auxiliary sparse embedding (ablation)SAM · COD10KMAE: 0.054 -> 0.039Improved
add mask prompt from full BLIP caption (ablation)SAM + EmbAux · CAMOS-measure: 0.805 -> 0.823Improved
add mask prompt from full BLIP caption (ablation)SAM + EmbAux · COD10Kmax F-measure: 0.751 -> 0.776Improved
use extracted first noun instead of full caption for prompt generation (ablation)SAM + EmbAux + P_init · CHAMELEONS-measure: 0.866 -> 0.882Improved
use extracted first noun instead of full caption (ablation)SAM + EmbAux + P_init · COD10Kmax F-measure: 0.776 -> 0.789Improved
use extracted first noun instead of full caption (ablation)SAM + EmbAux + P_init · CAMOMAE: 0.081 -> 0.080No clear effect
add Adaptive Refinement Module to refine the noun prompt (ablation)SAM + EmbAux + P_init noun · CHAMELEONS-measure: 0.882 -> 0.932Improved
add Adaptive Refinement Module (ablation)SAM + EmbAux + P_init noun · CAMOmax F-measure: 0.807 -> 0.883Improved
add Adaptive Refinement Module (ablation)SAM + EmbAux + P_init noun · COD10KS-measure: 0.846 -> 0.909Improved
add Adaptive Refinement Module (ablation)SAM + EmbAux + P_init noun · COD10KMAE: 0.036 -> 0.020Improved

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