AI Paper Atlas

Research map / Detection and segmentation / CNN features

ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection

Sheng Ye, Xin Chen, Yan Zhang, Xianming Lin, Liujuan Cao

ICCV 2025 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 22 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 MFMM to the baseline (ablation)ESCNet baseline · COD10KMAE: 0.037 -> 0.025Improved
add AETP on top of MFMM (ablation)ESCNet · COD10KS-measure: 0.863 -> 0.877Improved
add DSFA on top of AETP + MFMM (ablation)ESCNet · COD10KMAE: 0.023 -> 0.021Improved
add DSFA on top of AETP + MFMM (ablation)ESCNet · CAMOS-measure: 0.876 -> 0.871Hurt
add DSFA on top of AETP + MFMM (ablation)ESCNet · NC4Kweighted F-measure: 0.846 -> 0.859Improved
use the edge branch instead of the Laplacian branch in MFMM (ablation)ESCNet · COD10KMAE: 0.028 -> 0.026Improved
use all three branches (mask, edge, Laplace) in MFMM instead of mask only (ablation)ESCNet · COD10KMAE: 0.025 -> 0.021Improved
increase MFMM blocks from 1 to 2 (ablation)ESCNet · COD10KMAE: 0.033 -> 0.026Improved
increase MFMM blocks from 3 to the full configuration (ablation)ESCNet · COD10KMAE: 0.023 -> 0.021Improved
use edge information to compute deformable offsets in DSFA (ablation)ESCNet · qualitative offset visualizationoffset focusImproved
ESCNet vs CamoFormerESCNet · NC4Kweighted F-measure: 0.847 -> 0.859Improved
ESCNet vs CamoFormerESCNet · CAMOS-measure: 0.872 -> 0.871Hurt

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