AI Paper Atlas

Research map / Detection and segmentation / CNN features

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Hongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, Xilin Chen

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 737 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 Dynamic Label Assignment (DLA) (ablation)Faster R-CNN R50-FPN · COCO valAP: 37.0 -> 38.2Improved
add Dynamic SmoothL1 Loss (DSL) (ablation)Faster R-CNN R50-FPN · COCO valAP: 37.0 -> 38.0Improved
add DSL on top of DLA (ablation)Faster R-CNN R50-FPN · COCO valAP: 38.2 -> 38.9Improved
add DLA and DSL, AP90 (ablation)Faster R-CNN R50-FPN · COCO valAP: 9.7 -> 15.2Improved
fix SmoothL1 beta at 2.0 instead of 1.0 (ablation)Faster R-CNN R50-FPN · COCO valAP: 37.0 -> 35.9Hurt
fix SmoothL1 beta at 0.5 instead of 1.0 (ablation)Faster R-CNN R50-FPN · COCO valAP: 37.0 -> 37.5Improved
vary K_I in DLA among 64, 75 and 100 (ablation)Dynamic R-CNN · COCO valAP: 38.1, 38.2, 37.9No clear effect
vary update interval C among 20, 100 and 500 (ablation)Dynamic R-CNN · COCO valAP: 38.0, 38.2, 38.1No clear effect
add dynamic training (DLA+DSL) to Mask R-CNN R50Mask R-CNN · COCO valAP: 37.5 -> 39.4Improved
add dynamic training (DLA+DSL) to Mask R-CNN R101Mask R-CNN · COCO valAP: 39.7 -> 41.8Improved
add dynamic training to RetinaNetRetinaNet R50-FPN · COCO valAP: 35.6 -> 36.3Improved
add dynamic training to Faster R-CNN on PASCAL VOCFaster R-CNN R50-FPN · PASCAL VOC2007 testAP: 47.2 -> 48.7Improved

Later papers that compared with this method

3 later accepted papers report Dynamic R-CNN* as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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