AI Paper Atlas

Research map / Detection and segmentation / CNN features

Hierarchical Context Embedding for Region-based Object Detection

Zhao-Min Chen, Xin Jin, Borui Zhao, Xiu-Shen Wei, Yanwen Guo

ECCV 2020 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 32 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 image-level multi-label learning (MLL) (ablation)FPN · COCO 2017 val (ResNet-50-FPN)AP: 36.3 -> 36.8Improved
add instance-level context embedding on top of MLL (ablation)FPN · COCO 2017 val (ResNet-50-FPN)AP: 36.8 -> 37.8Improved
add global-level context embedding (ablation)FPN · COCO 2017 val (ResNet-50-FPN)AP: 37.8 -> 38.4Improved
add feature fusion in training (ablation)FPN with MLL · COCO 2017 val (ResNet-50-FPN)AP: 36.8 -> 37.6Improved
add confidence fusion in training (ablation)FPN with MLL · COCO 2017 val (ResNet-50-FPN)AP: 36.8 -> 37.4Improved
train with both fusions instead of feature fusion only (ablation)FPN with MLL · COCO 2017 val (ResNet-50-FPN)AP: 37.6 -> 38.4Improved
test with both branches instead of feature fusion branch only (ablation)HCE FPN · COCO 2017 val (ResNet-50-FPN)AP: 38.2 -> 38.4No clear effect
use feature fusion branch at inference vs baseline (ablation)HCE FPN · COCO 2017 val (ResNet-50-FPN)AP: 36.3 -> 38.2Improved
add HCE to FPNFPN · COCO 2017 val (ResNet-50-FPN)AP: 36.3 -> 38.4Improved
add HCE to FPNFPN · COCO 2017 val (ResNet-101-FPN)AP: 38.3 -> 40.0Improved
add HCE to Mask R-CNNMask R-CNN · COCO 2017 val (ResNet-50-FPN)AP: 37.3 -> 38.8Improved
add HCE to Cascade R-CNNCascade R-CNN · COCO 2017 val (ResNet-50-FPN)AP: 40.5 -> 41.7Improved

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