AI Paper Atlas

Research map / Detection and segmentation / CNN features

Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection

Lei Zhu, Zijun Deng, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, Pheng-Ann Heng

ECCV 2018 · Detection and segmentation › CNN features · approach: RGB salient object detection · 287 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 bidirectional pathway to FPN (ablation)FPN · SBU testBER: 5.78 -> 5.37Improved
add bidirectional pathway to FPN (ablation)FPN · UCF testBER: 7.70 -> 7.11Improved
add RAR modules to FPN (ablation)FPN · SBU testBER: 5.78 -> 4.33Improved
add RAR modules to FPN (ablation)FPN · UCF testBER: 7.70 -> 6.09Improved
use RAR modules instead of plain residual modules in the bidirectional network (ablation)BDRAR · SBU testBER: 4.23 -> 3.64Improved
use RAR modules instead of plain residual modules in the bidirectional network (ablation)BDRAR · UCF testBER: 6.71 -> 5.30Improved
add recurrence to attention residual module (2 steps vs 1) (ablation)BDAR · SBU testBER: 3.74 -> 3.64Improved
add recurrence to attention residual module (2 steps vs 1) (ablation)BDAR · UCF testBER: 6.19 -> 5.30Improved
increase recurrent steps from 2 to 3 (ablation)BDRAR · SBU testBER: 3.64 -> 3.89Hurt
share weights across recurrent steps in RAR (ablation)BDRAR · SBU testBER: 3.89 -> 3.64Improved
share weights across recurrent steps in RAR (ablation)BDRAR · UCF testBER: 5.66 -> 5.30Improved
use BDRAR instead of DSCDSC · SBU testBER: 5.59 -> 3.64Improved

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