AI Paper Atlas

Research map / Detection and segmentation / CNN features

Optimizing the F-Measure for Threshold-Free Salient Object Detection

Kai Zhao, Shanghua Gao, Wenguan Wang, Ming-Ming Cheng

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 94 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
train with FLoss instead of cross-entropyDSS · ECSSD (MSRA-B)MeanF: .889 -> .903Improved
train with FLoss instead of cross-entropyDSS · ECSSD (MSRA-B)MAE (lower better): .060 -> .050Improved
train with FLoss instead of cross-entropyDSS · DUT-OMRON (MSRA-B)MaxF: .761 -> .777Improved
train with FLoss instead of cross-entropyAmulet · ECSSD (MSRA-B)MaxF: .881 -> .894Improved
train with FLoss instead of cross-entropyAmulet · SOD (MSRA-B)MeanF: .776 -> .800Improved
train with FLoss instead of cross-entropyDHS · HKU-IS (MSRA-B)MaxF: .835 -> .859Improved
train with FLoss instead of cross-entropyDHS · DUT-OMRON (MSRA-B)MAE (lower better): .078 -> .079No clear effect
use relaxed F-measure loss instead of its log version (Log-FLoss) (ablation)DSS · ECSSD (MSRA-B)MeanF: .891 -> .903Improved
use relaxed F-measure loss instead of its log version (Log-FLoss) (ablation)DSS · DUT-OMRON (MSRA-B)MAE (lower better): .062 -> .067Hurt
use relaxed F-measure loss instead of its log version (Log-FLoss) (ablation)DSS · ECSSD (MSRA-B)MAE (lower better): .057 -> .050Improved
use FLoss instead of balanced cross-entropy (ablation)DSS · ECSSD (MSRA-B)MeanF: .890 -> .903Improved
use balanced cross-entropy instead of plain cross-entropy (ablation)DSS · ECSSD (MSRA-B)MeanF: .889 -> .890No clear effect

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