{"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/muxconv-information-multiplexing-in","title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","arxiv_id":"2003.13880","date":"2020-03-31","proceeding":"CVPR 2020 6","authors":["Zhichao Lu","Kalyanmoy Deb","Vishnu Naresh Boddeti"],"abstract":"Convolutional neural networks have witnessed remarkable improvements in computational efficiency in recent years. A key driving force has been the idea of trading-off model expressivity and efficiency through a combination of $1\\times 1$ and depth-wise separable convolutions in lieu of a standard convolutional layer. The price of the efficiency, however, is the sub-optimal flow of information across space and channels in the network. To overcome this limitation, we present MUXConv, a layer that is designed to increase the flow of information by progressively multiplexing channel and spatial information in the network, while mitigating computational complexity. Furthermore, to demonstrate the effectiveness of MUXConv, we integrate it within an efficient multi-objective evolutionary algorithm to search for the optimal model hyper-parameters while simultaneously optimizing accuracy, compactness, and computational efficiency. On ImageNet, the resulting models, dubbed MUXNets, match the performance (75.3% top-1 accuracy) and multiply-add operations (218M) of MobileNetV3 while being 1.6$\\times$ more compact, and outperform other mobile models in all the three criteria. MUXNet also performs well under transfer learning and when adapted to object detection. On the ChestX-Ray 14 benchmark, its accuracy is comparable to the state-of-the-art while being $3.3\\times$ more compact and $14\\times$ more efficient. Similarly, detection on PASCAL VOC 2007 is 1.2% more accurate, 28% faster and 6% more compact compared to MobileNetV2. Code is available from https://github.com/human-analysis/MUXConv","url_abs":"https://arxiv.org/abs/2003.13880v2","url_pdf":"https://arxiv.org/pdf/2003.13880v2.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":"muxconv-information-multiplexing-in","repo_url":"https://github.com/human-analysis/MUXConv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pneumonia-detection","task_name":"Pneumonia Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"MUXNet-m","rank_in_archive_order":58,"of":265,"metrics":{"Percentage correct":"98.0","Top-1 Accuracy":"98.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"MUXNet-m","rank_in_archive_order":56,"of":211,"metrics":{"PARAMS":"2.1M","Percentage correct":"86.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MUXNet-l","rank_in_archive_order":909,"of":1060,"metrics":{"GFLOPs":"0.636","Number of params":"4.0M","Top 1 Accuracy":"76.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MUXNet-m","rank_in_archive_order":953,"of":1060,"metrics":{"GFLOPs":"0.436","Number of params":"3.4M","Top 1 Accuracy":"75.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MUXNet-s","rank_in_archive_order":1006,"of":1060,"metrics":{"GFLOPs":"0.234","Number of params":"2.4M","Top 1 Accuracy":"71.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MUXNet-xs","rank_in_archive_order":1041,"of":1060,"metrics":{"GFLOPs":"0.132","Number of params":"1.8M","Top 1 Accuracy":"66.7%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"MUXNet-m","rank_in_archive_order":7,"of":41,"metrics":{"FLOPS":"200M","Parameters":"2.1M","Top-1 Error Rate":"2.0%"},"uses_additional_data":false},{"leaderboard":"/sota/architecture-search-on-cifar-10-image","task":"Neural Architecture Search","dataset":"CIFAR-10 Image Classification","model":"MUXNet-m","rank_in_archive_order":5,"of":19,"metrics":{"FLOPS":"200M","Params":"2.1M","Percentage error":"2.0"},"uses_additional_data":true},{"leaderboard":"/sota/neural-architecture-search-on-cifar-100-1","task":"Neural Architecture Search","dataset":"CIFAR-100","model":"MUXNet-m","rank_in_archive_order":5,"of":13,"metrics":{"FLOPS":"200M","PARAMS":"2.1M","Percentage Error":"13.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"MUXNet-l","rank_in_archive_order":80,"of":135,"metrics":{"Accuracy":"76.6","MACs":"318M","Params":"4.0M","Top-1 Error Rate":"23.4"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"MUXNet-m","rank_in_archive_order":111,"of":135,"metrics":{"Accuracy":"75.3","MACs":"218M","Params":"3.4M","Top-1 Error Rate":"24.7"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"MUXNet-s","rank_in_archive_order":127,"of":135,"metrics":{"Accuracy":"71.6","MACs":"117M","Params":"2.4M","Top-1 Error Rate":"28.4"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"MUXNet-xs","rank_in_archive_order":131,"of":135,"metrics":{"Accuracy":"66.7","MACs":"66M","Params":"1.8M","Top-1 Error Rate":"33.3"},"uses_additional_data":false},{"leaderboard":"/sota/pneumonia-detection-on-chestx-ray14","task":"Pneumonia Detection","dataset":"ChestX-ray14","model":"MUXNet-m","rank_in_archive_order":4,"of":5,"metrics":{"AUROC":"0.841","FLOPS":"200M","Params":"2.1M"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"MUXNet-m + PPM","rank_in_archive_order":225,"of":235,"metrics":{"Validation mIoU":"35.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"MUXNet-m + C1","rank_in_archive_order":227,"of":235,"metrics":{"Validation mIoU":"32.42"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}},"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/human-analysis/MUXConv","reach":null}],"summary":{"ran_fixture":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":"1d0dc1f5a5cb3014","entry":"hard_sigmoid","repo":"human-analysis/MUXConv","repo_kind":"official","path":"muxnet.py","file_url":"https://github.com/human-analysis/MUXConv/blob/HEAD/muxnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d0dc1f5a5cb3014"}},{"code_sha256_prefix":"e53d939c086be11f","entry":"hard_swish","repo":"human-analysis/MUXConv","repo_kind":"official","path":"muxnet.py","file_url":"https://github.com/human-analysis/MUXConv/blob/HEAD/muxnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e53d939c086be11f"}},{"code_sha256_prefix":"1ab2898fd19b53d9","entry":"sigmoid","repo":"human-analysis/MUXConv","repo_kind":"official","path":"muxnet.py","file_url":"https://github.com/human-analysis/MUXConv/blob/HEAD/muxnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ab2898fd19b53d9"}},{"code_sha256_prefix":"751e25dde57ac9c5","entry":"infer","repo":"human-analysis/MUXConv","repo_kind":"official","path":"transfer_cifar.py","file_url":"https://github.com/human-analysis/MUXConv/blob/HEAD/transfer_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"751e25dde57ac9c5"}},{"code_sha256_prefix":"86268981ba436430","entry":"train","repo":"human-analysis/MUXConv","repo_kind":"official","path":"transfer_cifar.py","file_url":"https://github.com/human-analysis/MUXConv/blob/HEAD/transfer_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"86268981ba436430"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}