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

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

25 Apr 2019arXiv:1904.11492archive 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, 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. 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 observe that this simplified design shares similar structure with Squeeze-Excitation Network (SENet). Hence we unify them into a three-step general framework for global context modeling. Within the general framework, we design a better instantiation, called the global context (GC) block, which is lightweight and can effectively model the global context. The lightweight property allows us to apply it for multiple layers in a backbone network to construct a global context network (GCNet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks. The code and configurations are released at https://github.com/xvjiarui/GCNet.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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
Oichii/DeepPulse-pytorch mentioned on GitHubpytorch report
czero69/acomoeye-NN mentioned on GitHubtf report
zhusiling/GCNet mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmdetection pytorchApache-2.0 report
open-mmlab/mmpose pytorchApache-2.0 report
open-mmlab/mmsegmentation pytorchApache-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 DetectionObject Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r16) mask AP 40.9 #70 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r16) mask AP 41.5% #60 of 112 Archive leaderboard report
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r16) AP50 66.9 #93 of 220 Archive leaderboard report
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r16) AP75 52.2 #93 of 220 Archive leaderboard report
Object Detection COCO minival GCNet (ResNeXt-101 + DCN + cascade + GC r16) box AP 47.9 #93 of 220 Archive leaderboard report
Object Detection COCO minival GCnet (ResNet-50-FPN, GRoIE) AP50 62.4 #178 of 220 Archive leaderboard report
Object Detection COCO minival GCnet (ResNet-50-FPN, GRoIE) AP75 44 #178 of 220 Archive leaderboard report
Object Detection COCO minival GCnet (ResNet-50-FPN, GRoIE) APL 52.5 #178 of 220 Archive leaderboard report
Object Detection COCO minival GCnet (ResNet-50-FPN, GRoIE) APM 44.4 #178 of 220 Archive leaderboard report
Object Detection COCO minival GCnet (ResNet-50-FPN, GRoIE) APS 24.2 #178 of 220 Archive leaderboard report
Object Detection COCO minival GCnet (ResNet-50-FPN, GRoIE) box AP 40.3 #178 of 220 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP50 67.6 #106 of 225 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) AP75 52.7 #106 of 225 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) Operations per network pass 54.8G #106 of 225 Archive leaderboard report
Object Detection COCO test-dev GCNet (ResNeXt-101 + DCN + cascade + GC r4) box mAP 48.4 #106 of 225 Archive leaderboard report
Object Detection COCO-O GCNet (RX-101-32x4d-DCN) Average mAP 26.0 #25 of 45 Archive leaderboard report
Object Detection COCO-O GCNet (RX-101-32x4d-DCN) Effective Robustness 4.38 #25 of 45 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

Introduced by this paper: GCNet, Global Context Block

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCascade Mask R-CNNCascade R-CNNConvolutionCosine AnnealingDeformable ConvolutionDense ConnectionsFPNGCNetGlobal Average PoolingGlobal Context BlockGrouped ConvolutionKaiming InitializationLayer NormalizationLinear Warmup With Cosine AnnealingMask R-CNNMax PoolingNon-Local BlockNon-Local OperationRPNRandom Horizontal FlipRandom Resized CropReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIAlignSENetSGD with MomentumSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStep DecayWeight Decay

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