Attention-guided Context Feature Pyramid Network for Object Detection

23 May 2020Junxu CaoQi ChenJun GuoRuichao Shi

For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question. In this paper, to tackle this issue, we build a novel architecture, called Attention-guided Context Feature Pyramid Network (AC-FPN), that exploits discriminative information from various large receptive fields via integrating attention-guided multi-path features... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Object Detection COCO test-dev AC-FPN Cascade R-CNN (X-152-32x8d-FPN-IN5k, multi scale, only CEM) box AP 51.9 # 7
AP50 70.4 # 8
AP75 57 # 6
APS 34.2 # 7
APM 54.8 # 8
APL 64.7 # 6
Object Detection COCO test-dev AC-FPN Cascade R-CNN(ResNet-101, single scale) box AP 45 # 26
AP50 64.4 # 30
AP75 49 # 29
APS 26.9 # 30
APM 47.7 # 29
APL 56.6 # 31

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