AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Seeing the Unseen: A Semantic Alignment and Context-Aware Prompt Framework for Open-Vocabulary Camouflaged Object Segmentation

Peng Ren, Tian Bai, Jing Sun, Fuming Sun

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 5 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 CAP prompts to baseline (ablation)Baseline CLIP-ConvNeXt-L · OVCamo ablationcSm: 0.546 -> 0.623Improved
add CAFS to baseline+CAP (ablation)Ours · OVCamo ablationcIoU: 0.415 -> 0.506Improved
add TQD to baseline+CAP+CAFS (ablation)Ours · OVCamo ablationcIoU: 0.506 -> 0.540Improved
use CAP instead of handcrafted CLIP templates (ablation)Ours · OVCamo ablationcIoU: 0.500 -> 0.540Improved
use CAP instead of OVCoser templates (ablation)Ours · OVCamo ablationcSm: 0.651 -> 0.667Improved
use CAP instead of CoOp (ablation)Ours · OVCamo ablationcIoU: 0.513 -> 0.540Improved
use CAP instead of CoCoOp (ablation)Ours · OVCamo ablationcIoU: 0.532 -> 0.540Improved
extract visual tokens from F2/F3-level feature rather than global F4v (ablation)Ours · OVCamo ablationcIoU: 0.526 -> 0.540Improved
gating mechanism instead of element-wise addition in CAP (ablation)Ours · OVCamo ablationcSm: 0.655 -> 0.667Improved
CAFS interaction instead of simple multiplication (ablation)Ours · OVCamo ablationcIoU: 0.526 -> 0.540Improved
add semantic consistency loss Lsc (ablation)Ours · OVCamo ablationcIoU: 0.528 -> 0.540Improved
use CAFS-refined features in TQD instead of original CLIP features (ablation)Ours · OVCamo ablationcSm: 0.646 -> 0.667Improved

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