AI Paper Atlas

Research map / Detection and segmentation / CNN features

Offset Bin Classification Network for Accurate Object Detection

Heqian Qiu, Hongliang Li, Qingbo Wu, Hengcan Shi

CVPR 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 40 citations (OpenAlex)

Check 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
Replace bounding box regression with offset bin classificationFaster R-CNN with ResNet-50-FPN · VOC2007 testAP: 45.0 -> 49.0Improved
Replace bounding box regression with offset bin classificationFaster R-CNN with ResNet-50-FPN · MS-COCO test-devAP: 36.6 -> 40.5Improved
Replace regression branches with offset bin classificationCascade R-CNN with ResNet-101-FPN · VOC2007 testAP: 51.0 -> 51.9Improved
Replace regression branches with offset bin classificationCascade R-CNN with ResNet-101-FPN · MS-COCO test-devAP: 42.4 -> 44.4Improved
Add expectation-based offset prediction (ablation)Offset bin classification · VOC2007 testAP: 45.8 -> 47.5Improved
Add hierarchical focusing offset prediction (ablation)Offset bin classification · VOC2007 testAP: 45.8 -> 47.5Improved
Add both expectation-based and hierarchical focusing offset prediction (ablation)Offset bin classification · VOC2007 testAP: 45.8 -> 49.0Improved
Replace Smooth L1 loss with offset bin classification (ablation)ResNet-50-FPN detector · VOC2007 testAP: 45.0 -> 47.5Improved
Increase Smooth L1 division point from β = 1.0 to β = 1.5 (ablation)ResNet-50-FPN detector · VOC2007 testAP: 45.0 -> 44.3Hurt
Increase Smooth L1 division point from β = 1.0 to β = 2.0 (ablation)ResNet-50-FPN detector · VOC2007 testAP: 45.0 -> 44.2Hurt
Use two hierarchical focusing stages instead of one (ablation)Offset bin classification · VOC2007 testAP: 47.5 -> 49.0Improved
Use three hierarchical focusing stages instead of two (ablation)Offset bin classification · VOC2007 testAP: 49.0 -> 48.8Hurt

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