{"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/cas-vit-convolutional-additive-self-attention","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","arxiv_id":"2408.03703","date":"2024-08-07","proceeding":null,"authors":["Tianfang Zhang","Lei LI","Yang Zhou","Wentao Liu","Chen Qian","Jenq-Neng Hwang","Xiangyang Ji"],"abstract":"Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on resource-constrained scenarios and real-time applications, such as mobile devices, although considerable efforts have been made in previous works. In this paper, we introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications. Firstly, we argue that the capability of token mixers to obtain global contextual information hinges on multiple information interactions, such as spatial and channel domains. Subsequently, we propose Convolutional Additive Token Mixer (CATM) employing underlying spatial and channel attention as novel interaction forms. This module eliminates troublesome complex operations such as matrix multiplication and Softmax. We introduce Convolutional Additive Self-attention(CAS) block hybrid architecture and utilize CATM for each block. And further, we build a family of lightweight networks, which can be easily extended to various downstream tasks. Finally, we evaluate CAS-ViT across a variety of vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation. Our M and T model achieves 83.0\\%/84.1\\% top-1 with only 12M/21M parameters on ImageNet-1K. Meanwhile, throughput evaluations on GPUs, ONNX, and iPhones also demonstrate superior results compared to other state-of-the-art backbones. Extensive experiments demonstrate that our approach achieves a better balance of performance, efficient inference and easy-to-deploy. Our code and model are available at: \\url{https://github.com/Tianfang-Zhang/CAS-ViT}","url_abs":"https://arxiv.org/abs/2408.03703v2","url_pdf":"https://arxiv.org/pdf/2408.03703v2.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":"cas-vit-convolutional-additive-self-attention","repo_url":"https://github.com/tianfang-zhang/cas-vit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cas-vit-convolutional-additive-self-attention","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":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"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":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAS-ViT-T","rank_in_archive_order":352,"of":1060,"metrics":{"GFLOPs":"3.597","Number of params":"21.76M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAS-ViT-M","rank_in_archive_order":475,"of":1060,"metrics":{"GFLOPs":"1.887","Number of params":"12.42M","Top 1 Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAS-ViT-S","rank_in_archive_order":662,"of":1060,"metrics":{"GFLOPs":"0.932","Number of params":"5.76M","Top 1 Accuracy":"81.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAS-ViT-XS","rank_in_archive_order":811,"of":1060,"metrics":{"GFLOPs":"0.56","Number of params":"3.2M","Top 1 Accuracy":"78.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.03703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03703"}},"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://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tianfang-zhang/cas-vit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_honours":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"a4cb506c560f097d","entry":"Stage","repo":"tianfang-zhang/cas-vit","repo_kind":"official","path":"classification/model/rcvit.py","file_url":"https://github.com/tianfang-zhang/cas-vit/blob/HEAD/classification/model/rcvit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4cb506c560f097d"}},{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"tianfang-zhang/cas-vit","repo_kind":"official","path":"classification/model/rcvit.py","file_url":"https://github.com/tianfang-zhang/cas-vit/blob/HEAD/classification/model/rcvit.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"979fc7d0ba424da1","entry":"get_parameter_groups","repo":"tianfang-zhang/cas-vit","repo_kind":"official","path":"classification/optim_factory.py","file_url":"https://github.com/tianfang-zhang/cas-vit/blob/HEAD/classification/optim_factory.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"979fc7d0ba424da1"}},{"code_sha256_prefix":"b72ba06382340c08","entry":"stem","repo":"tianfang-zhang/cas-vit","repo_kind":"official","path":"classification/model/rcvit.py","file_url":"https://github.com/tianfang-zhang/cas-vit/blob/HEAD/classification/model/rcvit.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b72ba06382340c08"}},{"code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"tianfang-zhang/cas-vit","repo_kind":"official","path":"classification/utils.py","file_url":"https://github.com/tianfang-zhang/cas-vit/blob/HEAD/classification/utils.py","link_basis":"harvester_set","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":"b700fb0a3496b255"}},{"code_sha256_prefix":"199223de2f9704cf","entry":"get_num_layer_for_convnext","repo":"tianfang-zhang/cas-vit","repo_kind":"official","path":"classification/optim_factory.py","file_url":"https://github.com/tianfang-zhang/cas-vit/blob/HEAD/classification/optim_factory.py","link_basis":"harvester_set","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":"199223de2f9704cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}