AI Paper Atlas

Research map / Detection and segmentation / CNN features

Frequency-Spatial Entanglement Learning for Camouflaged Object Detection

Yanguang Sun, Chunyan Xu, Jian Yang, Hanyu Xuan, Lei Luo

ECCV 2024 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 126 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 Entanglement Transformer Block (ETB) to baseline (ablation)FSEL ResNet50-FPN baseline · CAMOMAE: 0.093 -> 0.076Improved
add Dual-domain Reverse Parser (DRP) to baseline (ablation)FSEL baseline · CAMOMAE: 0.093 -> 0.074Improved
add Joint Domain Perception Module (JDPM) to baseline (ablation)FSEL baseline · CAMOMAE: 0.093 -> 0.081Improved
combine ETB, DRP and JDPM (ablation)FSEL · CAMOMAE: 0.074 -> 0.067Improved
combine all three modules (ablation)FSEL · COD10KS-measure: 0.778 -> 0.830Improved
use frequency-only ETB instead of spatial-only ETB (ablation)ETB · CAMOMAE: 0.079 -> 0.075Improved
use full entangled ETB instead of frequency-only ETB (ablation)ETB · CAMOMAE: 0.075 -> 0.076No clear effect
use FSEL (Ours-R50) instead of FEDERCOD · CAMO, COD10K, NC4KMAE: 0.071 -> 0.067; 0.032 -> 0.031; 0.044 -> 0.042Improved
use FSEL PVTv2 variant instead of FSPNetCOD · COD10KMAE: 0.026 -> 0.021Improved

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