Papers › Compact Global Descriptor for Neural Networks

Compact Global Descriptor for Neural Networks

23 Jul 2019arXiv:1907.09665archive 2025-07-28

Xiangyu He, Ke Cheng, Qiang Chen, Qinghao Hu, Peisong Wang, Jian Cheng

Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks. Yet neither stacks of convolutional operations to enlarge receptive fields nor recent nonlocal modules is computationally efficient. In this paper, we present a generic family of lightweight global descriptors for modeling the interactions between positions across different dimensions (e.g., channels, frames). This descriptor enables subsequent convolutions to access the informative global features with negligible computational complexity and parameters. Benchmark experiments show that the proposed method can complete state-of-the-art long-range mechanisms with a significant reduction in extra computing cost. Code available at https://github.com/HolmesShuan/Compact-Global-Descriptor.

PaperPDFCode

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

Code

HolmesShuan/Compact-Global-Descriptor officialmentioned in papermentioned on GitHubpytorch 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

Audio ClassificationDeep AttentionImage ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MobileNet-224 (CGD) GFLOPs 1.198 #995 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNet-224 (CGD) Number of params 4.26M #995 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNet-224 (CGD) Top 1 Accuracy 72.56% #995 of 1060 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN + FPN + CGD box mAP 37.9 #215 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

Introduced by this paper: Compact Global Descriptor

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCompact Global DescriptorConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionFPNFaster R-CNNGlobal Average PoolingKaiming InitializationMax PoolingMobileNetV1Non Maximum SuppressionPointwise ConvolutionRPNRandom Horizontal FlipRandom Resized CropReLUResidual BlockResidual ConnectionRoIPoolSGD with MomentumSSDSoftmaxStep 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