Papers › Gated Channel Transformation for Visual Recognition

Gated Channel Transformation for Visual Recognition

25 Sep 2019CVPR 2020 6arXiv:1909.11519archive 2025-07-28

Zongxin Yang, Linchao Zhu, Yu Wu, Yi Yang

In this work, we propose a generally applicable transformation unit for visual recognition with deep convolutional neural networks. This transformation explicitly models channel relationships with explainable control variables. These variables determine the neuron behaviors of competition or cooperation, and they are jointly optimized with the convolutional weight towards more accurate recognition. In Squeeze-and-Excitation (SE) Networks, the channel relationships are implicitly learned by fully connected layers, and the SE block is integrated at the block-level. We instead introduce a channel normalization layer to reduce the number of parameters and computational complexity. This lightweight layer incorporates a simple l2 normalization, enabling our transformation unit applicable to operator-level without much increase of additional parameters. Extensive experiments demonstrate the effectiveness of our unit with clear margins on many vision tasks, i.e., image classification on ImageNet, object detection and instance segmentation on COCO, video classification on Kinetics.

PaperPDFConference PDFCode

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

Code

z-x-yang/GCT officialtf report
mnikitin/ECANet mentioned on GitHubmxnet report
mnikitin/channel-attention mentioned on GitHubmxnet 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

General ClassificationImage ClassificationInstance SegmentationObject DetectionSemantic SegmentationVideo Classificationimage-classificationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: GCT

GCT

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