AI Paper Atlas

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

Referring Camouflaged Object Detection

Xuying Zhang, Bowen Yin, Zheng Lin, Qibin Hou, Deng-Ping Fan, Ming‐Ming Cheng

TPAMI 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 65 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 referring images with salient objects (Ref-COD) to the FPN baselineFPN COD baseline · R2C7K test (overall)weighted F-measure: 0.604 -> 0.669Improved
add Referring Mask Generation module (ablation)R2CNet · R2C7K test (overall)weighted F-measure: 0.604 -> 0.661Improved
add Referring Feature Enrichment module (ablation)R2CNet · R2C7K test (overall)weighted F-measure: 0.604 -> 0.644Improved
combine RMG and RFE (ablation)R2CNet · R2C7K test (overall)weighted F-measure: 0.604 -> 0.669Improved
add reference branch to PFNetPFNet · R2C7K test (overall)S-measure: 0.791 -> 0.811Improved
add reference branch to BGNetBGNet · R2C7K test (overall)S-measure: 0.818 -> 0.840Improved
add reference branch to ZoomNextZoomNext · R2C7K test (overall)S-measure: 0.838 -> 0.850Improved
add reference branch to DGNetDGNet · R2C7K test (overall)S-measure: 0.816 -> 0.821Improved
apply Ref design to SOD modelsVSCode · CoSOD3KS-measure: 0.861 -> 0.874Improved
apply Ref design to SOD modelsVST++ · CoSOD3KS-measure: 0.846 -> 0.858Improved
use affine transformation and ConvLSTM fusion in RMG instead of multiply and concat (ablation)R2CNet · R2C7K test (overall)weighted F-measure: 0.656 -> 0.669Improved
add cross-scale path in RFE (ablation)R2CNet · R2C7K test (overall)weighted F-measure: 0.665 -> 0.669Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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