AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Gated Convolutional Networks with Hybrid Connectivity for Image Classification

Chuanguang Yang, Zhulin An, Hui Zhu, Xiaolong Hu, Kun Zhang, Kaiqiang Xu, Chao Li, Yongjun Xu

AAAI 2020 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 68 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use HCGNet-A3 instead of the strongest listed baselineCIFAR-10 image classification · CIFAR-10 testerror rate (%): 2.98 -> 2.14Improved
Use HCGNet-A3 instead of NASNet-ACIFAR-100 image classification · CIFAR-100 testerror rate (%): 16.03 -> 15.96Improved
Use HCGNet-C instead of AOGNet-40MImageNet classification · ImageNet 2012 validationTop-1 error rate (%): 19.8 -> 19.5Improved
Use HCGNet-C instead of AOGNet-40MImageNet classification · ImageNet 2012 validationTop-5 error rate (%): 4.9 -> 4.8Improved
Use HCGNet-B-FPN instead of ResNet-50-FPNMask-RCNN backbone · COCO val2017 detectionbounding-box AP50: 59.9 -> 60.6Improved
Use HCGNet-B-FPN instead of AOGNet-12M-FPNMask-RCNN backbone · COCO val2017 detectionbounding-box AP50:95: 38.0 -> 38.3Improved
Use HCGNet-B-FPN instead of AOGNet-12M-FPNMask-RCNN backbone · COCO val2017 instance segmentationmask AP50:95: 34.6 -> 35.2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy