{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gated-convolutional-networks-with-hybrid","title":"Gated Convolutional Networks with Hybrid Connectivity for Image Classification","arxiv_id":"1908.09699","date":"2019-08-26","proceeding":null,"authors":["Chuanguang Yang","Zhulin An","Hui Zhu","Xiaolong Hu","Kun Zhang","Kaiqiang Xu","Chao Li","Yongjun Xu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1908.09699v3","url_pdf":"https://arxiv.org/pdf/1908.09699v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gated-convolutional-networks-with-hybrid","repo_url":"https://github.com/winycg/HCGNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"network-dissection","method_name":"Network Dissection"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"HCGNet-A3","rank_in_archive_order":66,"of":265,"metrics":{"Percentage correct":"97.86"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"HCGNet-A2","rank_in_archive_order":73,"of":265,"metrics":{"Percentage correct":"97.71"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"HCGNet-A1","rank_in_archive_order":97,"of":265,"metrics":{"Percentage correct":"96.85"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"HCGNet-A3","rank_in_archive_order":80,"of":211,"metrics":{"PARAMS":"11.4M","Percentage correct":"84.04"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"HCGNet-A2","rank_in_archive_order":87,"of":211,"metrics":{"PARAMS":"3.1M","Percentage correct":"83.46"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"HCGNet-A1","rank_in_archive_order":112,"of":211,"metrics":{"PARAMS":"1.1M","Percentage correct":"81.87"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"HCGNet-C","rank_in_archive_order":700,"of":1060,"metrics":{"GFLOPs":"7.1","Number of params":"42.2M","Top 1 Accuracy":"80.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"HCGNet-B","rank_in_archive_order":828,"of":1060,"metrics":{"GFLOPs":"2.0","Number of params":"12.9M","Top 1 Accuracy":"78.5%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.09699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09699"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/winycg/HCGNet","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"b261f3da78055651","entry":"CrossEntropyLoss_label_smooth","repo":"winycg/HCGNet","repo_kind":"official","path":"main_imagenet.py","file_url":"https://github.com/winycg/HCGNet/blob/HEAD/main_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b261f3da78055651"}},{"code_sha256_prefix":"33ba52fc17e89516","entry":"mixup_criterion","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"33ba52fc17e89516"}},{"code_sha256_prefix":"8897714b1e9b6396","entry":"mixup_data","repo":"winycg/HCGNet","repo_kind":"official","path":"main_cifar.py","file_url":"https://github.com/winycg/HCGNet/blob/HEAD/main_cifar.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8897714b1e9b6396"}},{"code_sha256_prefix":"3d04404ba40305cc","entry":"mixup_data","repo":"winycg/HCGNet","repo_kind":"official","path":"main_imagenet.py","file_url":"https://github.com/winycg/HCGNet/blob/HEAD/main_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d04404ba40305cc"}},{"code_sha256_prefix":"eebcaba9a7bebae9","entry":"fast_collate","repo":"winycg/HCGNet","repo_kind":"official","path":"main_imagenet.py","file_url":"https://github.com/winycg/HCGNet/blob/HEAD/main_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eebcaba9a7bebae9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}