AI Paper Atlas

Research map / Detection and segmentation / CNN features

AP-Loss for Accurate One-Stage Object Detection

Kean Chen, Weiyao Lin, Jianguo Li, John See, Ji Wang, Junni Zou

TPAMI 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 87 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
replace CE-loss+OHEM with AP-lossRetinaNet-ResNet50 · VOC2007 testAP: 49.1 -> 53.1Improved
replace Focal loss with AP-lossRetinaNet-ResNet50 · COCO minivalAP: 33.9 -> 35.0Improved
replace CE-loss+OHEM with AP-lossSSD-VGG16 · VOC2007 testAP: 43.6 -> 45.2Improved
use AP-loss instead of AUC-lossRetinaNet-ResNet50 · COCO minivalAP: 25.5 -> 35.0Improved
use Focal loss instead of CE-loss+OHEMSSD-VGG16 · VOC2007 testAP: 43.6 -> 39.3Hurt
increase batch size from 1 to 8 (ablation)AP-Loss RetinaNet · VOC2007 testAP: 52.4 -> 53.1Improved
set step function delta to 1 rather than 0.25 (ablation)AP-Loss RetinaNet · VOC2007 testAP: 50.2 -> 53.1Improved
set step function delta to 1 rather than 4 (ablation)AP-Loss RetinaNet · VOC2007 testAP: 50.5 -> 53.1Improved
add interpolated AP (ablation)AP-Loss RetinaNet · VOC2007 testAP: 52.6 -> 53.1Improved
add interpolated AP (ablation)AP-Loss RetinaNet · VOC2007 testAP75: 57.1 -> 58.1Improved
use AP-loss instead of Focal loss under Black Patch perturbationRetinaNet-ResNet50 · VOC2007 test (Black Patch)mAP50: 60.9 -> 65.2Improved
use AP-loss instead of Focal loss under Gaussian noiseRetinaNet-ResNet50 · VOC2007 test (Gaussian Noise)mAP50: 65.7 -> 68.8Improved

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