AI Paper Atlas

Research map / Detection and segmentation / CNN features

Improving SAM for Camouflaged Object Detection via Dual Stream Adapters

Jiaming Liu, Linghe Kong, Guihai Chen

ICCV 2025 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 16 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 dual stream adapter to SAM baseline (ablation)SAM-COD · COD10KS_m: .829 -> .865Improved
add bidirectional knowledge distillation (ablation)SAM-COD · COD10KS_m: .865 -> .870Improved
add mixed prompt embedding (ablation)SAM-COD · COD10KS_m: .870 -> .887Improved
use wavelet-filtered adapter instead of LoRA-style adapter (ablation)SAM-COD · COD10KS_m: .848 -> .887Improved
add discrete wavelet transform to adapter (ablation)SAM-COD · COD10KS_m: .868 -> .887Improved
add depth stream (dual-stream adapter) to RGB-only (ablation)SAM-COD · COD10KS_m: .881 -> .887Improved
use both model and modal distillation instead of a single one (ablation)SAM-COD · COD10KS_m: .875 -> .887Improved
order distillation PVT->RGB->Depth instead of PVT->Depth->RGB (ablation)SAM-COD · COD10KS_m: .880 -> .887Improved
include PVT embedding in mixed prompt embedding (ablation)SAM-COD · COD10KS_m: .873 -> .887Improved
SAM-COD (RGB) versus SAM-Adapter on COD10K structure measureRGB-only setting · COD10KS_m: .883 -> .881Hurt
SAM-COD versus PopNet on CHAMELEONRGB-D setting · CHAMELEONS_m: .910 -> .893Hurt

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