Papers › Global Context Networks

Global Context Networks

24 Dec 2020arXiv:2012.13375archive 2025-07-28

Yue Cao, Jiarui Xu, Stephen Lin, Fangyun Wei, Han Hu

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, 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 the non-local network are almost the same for different query positions. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further replace the one-layer transformation function of the non-local block by a two-layer bottleneck, which further reduces the parameter number considerably. The resulting network element, called the global context (GC) block, effectively models global context in a lightweight manner, allowing it to be applied at multiple layers of a backbone network to form a global context network (GCNet). Experiments show that GCNet generally outperforms NLNet on major benchmarks for various recognition tasks. The code and network configurations are available at https://github.com/xvjiarui/GCNet.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xvjiarui/GCNet officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP50 67.9 #50 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP75 48.4 #50 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r4) mask AP 44.7 #50 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP50 68.9 #42 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP75 49.6 #42 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) mask AP 45.4 #42 of 112 Archive leaderboard report
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP50 70.4 #70 of 220 Archive leaderboard report
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP75 56.1 #70 of 220 Archive leaderboard report
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r4) box AP 51.8 #70 of 220 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP50 70.9 #72 of 225 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP75 56.9 #72 of 225 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) box mAP 52.3 #72 of 225 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionGCNetGlobal Context BlockLayer NormalizationNon-Local BlockNon-Local OperationReLUResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections