AI Paper Atlas

Research map / Detection and segmentation / CNN features

Summarize and Search: Learning Consensus-Aware Dynamic Convolution for Co-Saliency Detection

Ni Zhang, Junwei Han, Nian Liu, Ling Shao

ICCV 2021 · Detection and segmentation › CNN features · approach: RGB salient object detection · 80 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 vanilla adaptive kernels (ablation)baseline · CoCAmax F-measure: 0.451 -> 0.495Improved
add vanilla common kernel (ablation)baseline · CoCAmax F-measure: 0.451 -> 0.497Improved
use large 3x3 adaptive kernels instead of 1x1 (ablation)CADC · CoCAmax F-measure: 0.495 -> 0.508Improved
use large 3x3 common kernel instead of 1x1 (ablation)CADC · CoCAmax F-measure: 0.497 -> 0.498Improved
combine large adaptive and common kernels (ablation)CADC · CoCAmax F-measure: 0.508 -> 0.511Improved
add multi-level dynamic convolution in first four decoders (ablation)CADC · CoCAmax F-measure: 0.511 -> 0.548Improved
add multi-level dynamic convolution (ablation)CADC · CoCAMAE: 0.144 -> 0.132Improved
add original DUTS class data to COCO-sub training (ablation)CADC · CoCAmax F-measure: 0.467 -> 0.494Improved
add normal synthesis only (ablation)CADC · CoCAmax F-measure: 0.494 -> 0.504Improved
add reverse synthesis only (ablation)CADC · CoCAmax F-measure: 0.494 -> 0.510Improved
use bidirectional (normal + reverse) synthesis (ablation)CADC · CoCAmax F-measure: 0.504 -> 0.548Improved
replace jigsaw synthesis with bidirectional copy-and-blend synthesis (ablation)CADC · CoCAmax F-measure: 0.537 -> 0.548Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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