{"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/edgenext-efficiently-amalgamated-cnn","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","arxiv_id":"2206.10589","date":"2022-06-21","proceeding":null,"authors":["Muhammad Maaz","Abdelrahman Shaker","Hisham Cholakkal","Salman Khan","Syed Waqas Zamir","Rao Muhammad Anwer","Fahad Shahbaz Khan"],"abstract":"In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to build resource-efficient general purpose networks due to their usefulness in several application areas. In this work, we strive to effectively combine the strengths of both CNN and Transformer models and propose a new efficient hybrid architecture EdgeNeXt. Specifically in EdgeNeXt, we introduce split depth-wise transpose attention (STDA) encoder that splits input tensors into multiple channel groups and utilizes depth-wise convolution along with self-attention across channel dimensions to implicitly increase the receptive field and encode multi-scale features. Our extensive experiments on classification, detection and segmentation tasks, reveal the merits of the proposed approach, outperforming state-of-the-art methods with comparatively lower compute requirements. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K, outperforming MobileViT with an absolute gain of 2.2% with 28% reduction in FLOPs. Further, our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K. The code and models are available at https://t.ly/_Vu9.","url_abs":"https://arxiv.org/abs/2206.10589v3","url_pdf":"https://arxiv.org/pdf/2206.10589v3.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":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/mmaaz60/EdgeNeXt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/alibaba-miil/solving_imagenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/amshaker/swiftformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/2023-MindSpore-1/ms-code-149","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/edgenext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/edgenext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"edgenext-efficiently-amalgamated-cnn","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mobilevit","method_name":"MobileViT"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EdgeNeXt-S","rank_in_archive_order":758,"of":1060,"metrics":{"GFLOPs":"2.6","Number of params":"5.6M","Top 1 Accuracy":"79.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EdgeNeXt-XXS","rank_in_archive_order":1013,"of":1060,"metrics":{"GFLOPs":"0.522","Number of params":"1.3M","Top 1 Accuracy":"71.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"EdgeNeXt","rank_in_archive_order":30,"of":51,"metrics":{"FLOPS":"8.7G","Mean IoU":"80.2%","Params":"6.5M"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.10589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10589"}},"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/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba-miil/solving_imagenet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amshaker/swiftformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mmaaz60/EdgeNeXt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-149","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/edgenext","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/edgenext","reach":null}],"summary":{"ran_violates":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"ran":1,"repositories":2}},"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":"17061f7e01a6fc86","entry":"str2bool","repo":"MS-Mind/MS-Code-02","repo_kind":"listed","path":"config.py","file_url":"https://github.com/MS-Mind/MS-Code-02/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17061f7e01a6fc86"}},{"code_sha256_prefix":"490b21bf78e1dd8c","entry":"checkpoint_filter_fn","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/convnext.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/convnext.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"490b21bf78e1dd8c"}},{"code_sha256_prefix":"990768f15029c37e","entry":"checkpoint_filter_fn","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/cait.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/cait.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"990768f15029c37e"}},{"code_sha256_prefix":"de23eca1d0c4deda","entry":"checkpoint_filter_fn","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/coat.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/coat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de23eca1d0c4deda"}},{"code_sha256_prefix":"ec39382a920dc48d","entry":"create_stem","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/cspnet.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/cspnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec39382a920dc48d"}},{"code_sha256_prefix":"99272339ad32648c","entry":"gen_relative_position_index","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/beit.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/beit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99272339ad32648c"}},{"code_sha256_prefix":"dd4963bc37f4070b","entry":"insert_cls","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/coat.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/coat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd4963bc37f4070b"}},{"code_sha256_prefix":"d2f354582c2bc6f9","entry":"interleave_blocks","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/byobnet.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/byobnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d2f354582c2bc6f9"}},{"code_sha256_prefix":"eb0a3a17d4e9e9a1","entry":"parse_args","repo":"MS-Mind/MS-Code-02","repo_kind":"listed","path":"config.py","file_url":"https://github.com/MS-Mind/MS-Code-02/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb0a3a17d4e9e9a1"}},{"code_sha256_prefix":"ccdb9b1e0c522c8d","entry":"remove_cls","repo":"alibaba-miil/solving_imagenet","repo_kind":"listed","path":"models/coat.py","file_url":"https://github.com/alibaba-miil/solving_imagenet/blob/HEAD/models/coat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ccdb9b1e0c522c8d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}