{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/binaryvit-pushing-binary-vision-transformers","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","arxiv_id":"2306.16678","date":"2023-06-29","proceeding":null,"authors":["Phuoc-Hoan Charles Le","Xinlin Li"],"abstract":"With the increasing popularity and the increasing size of vision transformers (ViTs), there has been an increasing interest in making them more efficient and less computationally costly for deployment on edge devices with limited computing resources. Binarization can be used to help reduce the size of ViT models and their computational cost significantly, using popcount operations when the weights and the activations are in binary. However, ViTs suffer a larger performance drop when directly applying convolutional neural network (CNN) binarization methods or existing binarization methods to binarize ViTs compared to CNNs on datasets with a large number of classes such as ImageNet-1k. With extensive analysis, we find that binary vanilla ViTs such as DeiT miss out on a lot of key architectural properties that CNNs have that allow binary CNNs to have much higher representational capability than binary vanilla ViT. Therefore, we propose BinaryViT, in which inspired by the CNN architecture, we include operations from the CNN architecture into a pure ViT architecture to enrich the representational capability of a binary ViT without introducing convolutions. These include an average pooling layer instead of a token pooling layer, a block that contains multiple average pooling branches, an affine transformation right before the addition of each main residual connection, and a pyramid structure. Experimental results on the ImageNet-1k dataset show the effectiveness of these operations that allow a binary pure ViT model to be competitive with previous state-of-the-art (SOTA) binary CNN models.","url_abs":"https://arxiv.org/abs/2306.16678v1","url_pdf":"https://arxiv.org/pdf/2306.16678v1.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":"binaryvit-pushing-binary-vision-transformers","repo_url":"https://github.com/phuoc-hoan-le/binaryvit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"deit","method_name":"DeiT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet-1k","task":"Image Classification","dataset":"imagenet-1k","model":"BinaryViT","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy":"70.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.16678","atlas_url":"https://app.syntology.ai/?focus=2306.16678","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2306.16678"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2306.16678\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2306.16678"},"call":"get_concepts_for_paper(arxiv_id=\"2306.16678\")"}],"by_repo":[{"repo":"phuoc-hoan-le/binaryvit","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e1980f2d24d48d684942faed2228282be4041cab689d62c96d96103f4e5a0b75","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}