Corner Proposal Network for Anchor-free, Two-stage Object Detection

27 Jul 2020Kaiwen DuanLingxi XieHonggang QiSong BaiQingming HuangQi Tian

The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals by finding potential corner keypoint combinations and then assigns a class label to each proposal by a standalone classification stage... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO test-dev CPNDet (Hourglass-104, multi-scale) box AP 49.2 # 13
AP50 67.3 # 20
AP75 53.7 # 15
APS 31.0 # 18
APM 51.9 # 16
APL 62.4 # 13

Methods used in the Paper