AI Paper Atlas

Research map / Detection and segmentation / CNN features

Reconcile Prediction Consistency for Balanced Object Detection

Keyang Wang, Lei Zhang

ICCV 2021 · Detection and segmentation › CNN features · approach: Box regression and loss design · 45 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 Harmonic loss (ablation)Faster R-CNN · MS COCO valAP: 37.3 -> 38.5Improved
add standard IoU loss to Harmonic loss (ablation)Faster R-CNN · MS COCO valAP: 38.5 -> 38.7Improved
add HIoU loss to Harmonic loss (ablation)Faster R-CNN · MS COCO valAP: 38.5 -> 39.2Improved
add Task-Contrastive loss to Harmonic loss (ablation)Faster R-CNN · MS COCO valAP: 38.3 -> 38.5Improved
raise HIoU gamma from 0.0 to 0.8 (ablation)Faster R-CNN · MS COCO valAP: 38.7 -> 39.2Improved
raise HIoU gamma from 0.8 to 1.0 (ablation)Faster R-CNN · MS COCO valAP: 39.2 -> 39.0Hurt
raise HIoU alpha from 1.5 to 2.5 (ablation)Faster R-CNN · MS COCO valAP: 39.2 -> 38.9Hurt
raise HIoU alpha from 0.5 to 1.5 (ablation)Faster R-CNN · MS COCO valAP: 38.9 -> 39.2Improved
add HarmonicDet lossFaster R-CNN ResNet-50-FPN · PASCAL VOC 2007 testAP: 51.7 -> 54.2Improved
add HarmonicDet lossSSD300 · PASCAL VOC 2007 testAP: 51.0 -> 54.5Improved
add HarmonicDet lossRefineDet512 · PASCAL VOC 2007 testAP: 56.3 -> 60.4Improved
add HarmonicDet lossRefineDet512 · PASCAL VOC 2007 testAP90: 19.6 -> 29.7Improved

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