AI Paper Atlas

Research map / Detection and segmentation / CNN features

Employing Deep Part-Object Relationships for Salient Object Detection

Yi Liu, Qiang Zhang, Dingwen Zhang, Jungong Han

ICCV 2019 · Detection and segmentation › CNN features · approach: RGB salient object detection · 113 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 TSPOANet on top of FLNet (ablation)FLNet baseline · ECSSDF-measure: 0.8250 -> 0.8816Improved
add TSPOANet on top of FLNet (ablation)FLNet baseline · ECSSDMAE: 0.0694 -> 0.0521Improved
use two-stream capsule assignment instead of single stream (ablation)POANet · ECSSDF-measure: 0.8706 -> 0.8816Improved
use two-stream capsule assignment instead of single stream (ablation)POANet · ECSSDMAE: 0.0644 -> 0.0521Improved
use FLNet instead of Conv+ReLU feature extractor (ablation)SSPOANet · ECSSDF-measure: 0.6545 -> 0.8706Improved
use FLNet instead of Conv+ReLU feature extractor (ablation)SSPOANet · ECSSDMAE: 0.1504 -> 0.0644Improved
use 4 or 8 streams instead of 2 (ablation)TSPOANet · ECSSDconvergence: non-convergence with 4 and 8 streams, works with 2Hurt
use TSPOANet instead of BMPTSPOANet · DUTSF-measure: 0.7505 -> 0.7993Improved
use TSPOANet instead of BMPTSPOANet · ECSSDMAE: 0.0447 -> 0.0515Mixed

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