AI Paper Atlas

Research map / Detection and segmentation / CNN features

Contour Knowledge Transfer for Salient Object Detection

Xin Li, Fan Yang, Hong Cheng, Wei Liu, Dinggang Shen

ECCV 2018 · Detection and segmentation › CNN features · approach: RGB salient object detection · 309 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 cross-domain connections (CDC) between contour and saliency branches (ablation)C2S-Net · ECSSDweighted F-measure: 0.793 -> 0.812Improved
add cross-domain connections (CDC) between contour and saliency branches (ablation)C2S-Net · ECSSDMAE: 0.103 -> 0.081Improved
use contour-to-saliency transferring (CTS) instead of averaging proposals (AVG-P) (ablation)C2S-Net + CDC · ECSSDweighted F-measure: 0.665 -> 0.743Improved
use contour-to-saliency transferring (CTS) instead of winner-take-all (WTA) (ablation)C2S-Net + CDC · ECSSDweighted F-measure: 0.732 -> 0.743Improved
replace joint training (SCJ) with alternating training (AT(3)) (ablation)C2S-Net + CDC + CTS · ECSSDweighted F-measure: 0.759 -> 0.837Improved
increase alternating training iterations from 1 to 3 (ablation)C2S-Net + CDC + CTS · ECSSDweighted F-measure: 0.778 -> 0.837Improved
increase alternating training iterations from 3 to 5 (ablation)C2S-Net + CDC + CTS · ECSSDweighted F-measure: 0.837 -> 0.838No clear effect
increase unlabeled training data from 10K to 30K images (ablation)C2S-Net + CDC + CTS + AT(3) · ECSSDweighted F-measure: 0.837 -> 0.852Improved
increase unlabeled training data from 10K to 30K images (ablation)C2S-Net + CDC + CTS + AT(3) · ECSSDMAE: 0.059 -> 0.054Improved
use unlabeled 10K training instead of weakly supervised WSSWSS · ECSSDMAE: 0.103 -> 0.059Improved
use 30K unlabeled images instead of fully supervised AmuletAmulet · ECSSDF-measure: 0.915 -> 0.910Hurt
use 30K unlabeled images instead of fully supervised DSSDSS · DUTS-TEF-measure: 0.813 -> 0.807Hurt

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