HoughNet: Integrating near and long-range evidence for bottom-up object detection

This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location... (read more)

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Object Detection COCO test-dev HoughNet (MS) box AP 46.4 # 26
AP50 65.1 # 31
AP75 50.7 # 33
APS 29.1 # 29
APM 48.5 # 34
APL 58.1 # 29

Methods used in the Paper