Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects

About

Concealed Object Segmentation (COS) encompasses a family of dense-prediction tasks, including camouflaged object detection, polyp segmentation, transparent object detection, and industrial defect inspection, where targets are visually entangled with their surroundings through different physical mechanisms. Existing methods either operate directly on RGB images or employ \emph{heterogeneous} decompositions (\eg, Fourier, wavelet) that redistribute spatial evidence across scale/frequency coefficients, making pixel-aligned cues less direct. We introduce a fundamentally different perspective: \textbf{homogeneous image decomposition} via Retinex theory, which factorizes an image into illumination and reflectance components within the \emph{same} spatial domain. Our key insight is that visual entanglement enforces appearance matching in the composite space, but this does \emph{not} necessitate simultaneous matching in both component spaces, a phenomenon we formalize as the \textbf{Discriminability Gap Theorem}. Crucially, we show that across diverse COS sub-tasks, the underlying physical processes systematically anti-correlate illumination and reflectance differences, yielding theoretical guarantees that Retinex decomposition preserves or strictly improves total foreground--background discriminability across the full physical regime, with anti-correlation maximizing the gain. Building on this, we propose \textbf{RIDE} comprising: (i) a Task-Driven Retinex Decomposition module that learns segmentation-optimal factorizations end-to-end; (ii) a Discriminability Gap Attention mechanism that adaptively exploits where decomposition helps; and (iii) a Camouflage-Breaking Contrastive loss operating in reflectance feature space.

Chunming He, Rihan Zhang, Dingming Zhang, Chengyu Fang, Longxiang Tang, Jingjia Feng, Fengyang Xiao, Sina Farsiu• 2026

Related benchmarks

TaskDatasetResultRank
Camouflaged Object DetectionCOD10K
S-measure (S_alpha)0.906
217
Camouflaged Object DetectionChameleon
S-measure (S_alpha)93.3
207
Camouflaged Object DetectionNC4K
M Score0.041
88
Camouflaged Object DetectionCAMO
S_alpha91.2
21
Polyp Image SegmentationETIS
mDice79.3
13
Concealed Defect DetectionCDS2K
S_alpha0.609
6
Transparent Object DetectionGDD
mIoU90.7
6
Showing 7 of 7 rows

Other info

Follow for update