{"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/dicenet-dimension-wise-convolutions-for","title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","arxiv_id":"1906.03516","date":"2019-06-08","proceeding":null,"authors":["Sachin Mehta","Hannaneh Hajishirzi","Mohammad Rastegari"],"abstract":"We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply light-weight convolutional filtering across each dimension of the input tensor while dimension-wise fusion efficiently combines these dimension-wise representations; allowing the DiCE unit to efficiently encode spatial and channel-wise information contained in the input tensor. The DiCE unit is simple and can be seamlessly integrated with any architecture to improve its efficiency and performance. Compared to depth-wise separable convolutions, the DiCE unit shows significant improvements across different architectures. When DiCE units are stacked to build the DiCENet model, we observe significant improvements over state-of-the-art models across various computer vision tasks including image classification, object detection, and semantic segmentation. On the ImageNet dataset, the DiCENet delivers 2-4% higher accuracy than state-of-the-art manually designed models (e.g., MobileNetv2 and ShuffleNetv2). Also, DiCENet generalizes better to tasks (e.g., object detection) that are often used in resource-constrained devices in comparison to state-of-the-art separable convolution-based efficient networks, including neural search-based methods (e.g., MobileNetv3 and MixNet. Our source code in PyTorch is open-source and is available at https://github.com/sacmehta/EdgeNets/","url_abs":"https://arxiv.org/abs/1906.03516v3","url_pdf":"https://arxiv.org/pdf/1906.03516v3.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":"dicenet-dimension-wise-convolutions-for","repo_url":"https://github.com/sacmehta/EdgeNets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dicenet-dimension-wise-convolutions-for","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"dice-unit","method_name":"DiCE Unit"},{"method_slug":"dicenet","method_name":"DiCENet"},{"method_slug":"dimconv","method_name":"DimConv"},{"method_slug":"dimfuse","method_name":"DimFuse"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"ssd","method_name":"SSD"},{"method_slug":"shufflenet-v2-block","method_name":"ShuffleNet V2 Block"},{"method_slug":"shufflenet-v2-downsampling-block","method_name":"ShuffleNet V2 Downsampling Block"},{"method_slug":"shufflenet-v2","method_name":"ShuffleNet v2"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"dice-unit","name":"DiCE Unit","full_name":"DiCE Unit"},{"slug":"dicenet","name":"DiCENet","full_name":"DiCENet"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DiCENet","rank_in_archive_order":957,"of":1060,"metrics":{"GFLOPs":"0.553","Top 1 Accuracy":"75.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"DiCENet","rank_in_archive_order":93,"of":99,"metrics":{"mIoU":"63.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"DiCENet","rank_in_archive_order":43,"of":51,"metrics":{"Mean IoU":"67.31%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"DiCENet","rank_in_archive_order":21,"of":29,"metrics":{"mIoU":"66.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1906.03516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03516"}},"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/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sacmehta/EdgeNets","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"a0258644126bee3c","entry":"activation_fn","repo":"sacmehta/EdgeNets","repo_kind":"official","path":"nn_layers/cnn_utils.py","file_url":"https://github.com/sacmehta/EdgeNets/blob/HEAD/nn_layers/cnn_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0258644126bee3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}