RepPoints V2: Verification Meets Regression for Object Detection

16 Jul 2020Yihong ChenZheng ZhangYue CaoLiwei WangStephen LinHan Hu

Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO test-dev RepPoints v2 (ResNeXt-101, DCN, multi-scale) box AP 52.1 # 7
AP50 70.1 # 10
AP75 57.5 # 7
APS 34.5 # 8
APM 54.6 # 10
APL 63.6 # 12
Object Detection COCO test-dev RepPoints v2 (ResNeXt-101, DCN) box AP 49.4 # 12
AP50 68.9 # 14
AP75 53.4 # 17
APS 30.3 # 19
APM 52.1 # 15
APL 62.3 # 14

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet