AI Paper Atlas

Research map / Detection and segmentation / CNN features

Instance-Level Relative Saliency Ranking with Graph Reasoning

Nian Liu, Long Li, Wangbo Zhao, Junwei Han, Ling Shao

TPAMI 2021 · Detection and segmentation › CNN features · approach: RGB salient object detection · 30 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 interaction relation graph G^r (ablation)Baseline I · Proposed dataset test setSA-SOR: 0.5147 -> 0.5339Improved
add local contrast graph G^l (ablation)G^r model · Proposed dataset test setSA-SOR: 0.5339 -> 0.5487Improved
add global contrast graph G^g (ablation)G^r+G^l model · Proposed dataset test setSA-SOR: 0.5487 -> 0.5568Improved
add person prior graph G^p (ablation)G^r+G^l+G^g model · Proposed dataset test setSA-SOR: 0.5568 -> 0.5616Improved
use graph reasoning instead of plain feature concatenation with same four features (ablation)Baseline II · Proposed dataset test setSA-SOR: 0.5419 -> 0.5616Improved
use K=8 subgraphs instead of K=16 (ablation)G^r · Proposed dataset test setSA-SOR: 0.5164 -> 0.5339Improved
use K=8 subgraphs instead of K=4 (ablation)G^r · Proposed dataset test setSA-SOR: 0.5160 -> 0.5339Improved
increase global context nodes from M=3 to M=7 (ablation)G^g · Proposed dataset test setSA-SOR: 0.5455 -> 0.5568Improved
increase global context nodes from M=7 to M=14 (ablation)G^g · Proposed dataset test setSA-SOR: 0.5568 -> 0.5568No clear effect
use ranking loss instead of Softmax with cross entropy (ablation)Full model · Proposed dataset test setSA-SOR: 0.5271 -> 0.5616Improved
add dynamic loss weight gamma=1 (ablation)Ranking loss · Proposed dataset test setSA-SOR: 0.5616 -> 0.5647Improved
increase gamma to 1.5 (ablation)Ranking loss · Proposed dataset test setSA-SOR: 0.5647 -> 0.5345Hurt

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