AI Paper Atlas

Research map / Detection and segmentation / CNN features

Towards High-Resolution Salient Object Detection

Yi Zeng, Pingping Zhang, Jianming Zhang, Zhe Lin, Huchuan Lu

ICCV 2019 · Detection and segmentation › CNN features · approach: RGB salient object detection · 233 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 LRN with attended patch sampling to GSN (ablation)GSN · HRSOD-TestF-beta: 0.842 -> 0.877Improved
add LRN with attended patch sampling to GSN (ablation)GSN · HRSOD-TestMAE: 0.047 -> 0.036Improved
use attended patch sampling instead of random patch sampling (ablation)GSN+LRN · HRSOD-TestF-beta: 0.860 -> 0.877Improved
use attended patch sampling instead of random patch sampling (ablation)GSN+LRN · HRSOD-TestS-measure: 0.871 -> 0.883Improved
add GLFN fusion on top of GSN+APS+LRN (ablation)GSN+APS+LRN · HRSOD-TestF-beta: 0.877 -> 0.888Improved
add GLFN fusion on top of GSN+APS+LRN (ablation)GSN+APS+LRN · HRSOD-TestMAE: 0.036 -> 0.030Improved
use GLFN instead of CRF post-processing (ablation)GSN+APS+LRN · HRSOD-TestS-measure: 0.875 -> 0.897Improved
add CRF post-processing to GSN (ablation)GSN · HRSOD-TestS-measure: 0.866 -> 0.852Hurt
add CRF post-processing to GSN (ablation)GSN · HRSOD-TestMAE: 0.047 -> 0.038Improved
train on DUTS plus HRSOD instead of DUTS onlyOurs · DUTS-TestF-beta: 0.796 -> 0.791Hurt
train on DUTS plus HRSOD instead of DUTS onlyOurs · HRSOD-TestF-beta: 0.857 -> 0.888Improved

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