GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

25 Apr 2019Yue CaoJiarui XuStephen LinFangyun WeiHan Hu

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an image... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Instance Segmentation COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r16) mask AP 40.9 # 8
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r16) box AP 47.9 # 8
AP50 66.9 # 8
AP75 52.2 # 7
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) box AP 48.4 # 12
AP50 67.6 # 15
AP75 52.7 # 15
Instance Segmentation COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r16) mask AP 41.5% # 7

Methods used in the Paper