Papers › Gated Convolutional Networks with Hybrid Connectivity for Image Classification

Gated Convolutional Networks with Hybrid Connectivity for Image Classification

26 Aug 2019arXiv:1908.09699archive 2025-07-28

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

We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual. Furthermore, SMG module is equipped with an efficient two-stage pipeline, which aims to DenseNet-like architectures that need to integrate all previous outputs, i.e., squeezing the incoming informative but redundant features gradually by hierarchical convolutions as a hourglass shape and then exciting it by multi-kernel depthwise convolutions, the output of which would be compact and hold more informative multi-scale features. We further develop a forget and an update gate by introducing the popular attention modules to implement the effective fusion instead of a simple addition between reused and new features. Due to the Hybrid Connectivity (nested combination of global dense and local residual) and Gated mechanisms, we called our network as the HCGNet. Experimental results on CIFAR and ImageNet datasets show that HCGNet is more prominently efficient than DenseNet, and can also significantly outperform state-of-the-art networks with less complexity. Moreover, HCGNet also shows the remarkable interpretability and robustness by network dissection and adversarial defense, respectively. On MS-COCO, HCGNet can consistently learn better features than popular backbones.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1908.09699")

Code

Syntology Ran 4 of 5 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 4 samples from 1 repository, 3 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

winycg/HCGNet 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

5 samples harvested; 4 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
2ran · fixture could not drive it
1unverified

Licence: 5 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from winycg/HCGNet. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

CrossEntropyLoss_label_smooth winycg/HCGNet/main_imagenet.py official repository ran · our draft was wrong no licence file found · pointer only · b261f3da78055651 · report
mixup_data winycg/HCGNet/main_cifar.py official repository ran · fixture could not drive it no licence file found · pointer only · 8897714b1e9b6396 · report
mixup_data winycg/HCGNet/main_imagenet.py official repository ran · fixture could not drive it no licence file found · pointer only · 3d04404ba40305cc · report
fast_collate winycg/HCGNet/main_imagenet.py official repository unverified no licence file found · pointer only · eebcaba9a7bebae9 · report
mixup_criterion identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 33ba52fc17e89516 · report

Tasks

Adversarial DefenseClassificationGeneral ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 HCGNet-A3 Percentage correct 97.86 #66 of 265 Archive leaderboard report
Image Classification CIFAR-10 HCGNet-A2 Percentage correct 97.71 #73 of 265 Archive leaderboard report
Image Classification CIFAR-10 HCGNet-A1 Percentage correct 96.85 #97 of 265 Archive leaderboard report
Image Classification CIFAR-100 HCGNet-A3 PARAMS 11.4M #80 of 211 Archive leaderboard report
Image Classification CIFAR-100 HCGNet-A3 Percentage correct 84.04 #80 of 211 Archive leaderboard report
Image Classification CIFAR-100 HCGNet-A2 PARAMS 3.1M #87 of 211 Archive leaderboard report
Image Classification CIFAR-100 HCGNet-A2 Percentage correct 83.46 #87 of 211 Archive leaderboard report
Image Classification CIFAR-100 HCGNet-A1 PARAMS 1.1M #112 of 211 Archive leaderboard report
Image Classification CIFAR-100 HCGNet-A1 Percentage correct 81.87 #112 of 211 Archive leaderboard report
Image Classification ImageNet HCGNet-C GFLOPs 7.1 #700 of 1060 Archive leaderboard report
Image Classification ImageNet HCGNet-C Number of params 42.2M #700 of 1060 Archive leaderboard report
Image Classification ImageNet HCGNet-C Top 1 Accuracy 80.5% #700 of 1060 Archive leaderboard report
Image Classification ImageNet HCGNet-B GFLOPs 2.0 #828 of 1060 Archive leaderboard report
Image Classification ImageNet HCGNet-B Number of params 12.9M #828 of 1060 Archive leaderboard report
Image Classification ImageNet HCGNet-B Top 1 Accuracy 78.5% #828 of 1060 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 ConvolutionAverage PoolingBatch NormalizationConcatenated Skip ConnectionConvolutionDense BlockDense ConnectionsDropoutGlobal Average PoolingInterpretabilityKaiming InitializationMax PoolingNetwork DissectionReLUSoftmax

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