{"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/spatial-channel-token-distillation-for-vision","title":"Spatial-Channel Token Distillation for Vision MLPs","arxiv_id":null,"date":"2022-07-23","proceeding":"International Conference on Machine Learning 2022 7","authors":["Yanxi Li","Xinghao Chen","Minjing Dong","Yehui Tang","Yunhe Wang","Chang Xu"],"abstract":"Recently, neural architectures with all Multi-layer Perceptrons (MLPs) have attracted great research interest from the computer vision community. However, the inefficient mixing of spatial-channel information causes MLP-like vision models to demand tremendous pre-training on large-scale datasets. This work solves the problem from a novel knowledge distillation perspective. We propose a novel Spatial-channel Token Distillation (STD) method, which improves the information mixing in the two dimensions by introducing distillation tokens to each of them. A mutual information regularization is further introduced to let distillation tokens focus on their specific dimensions and maximize the performance gain. Extensive experiments on ImageNet for several MLP-like architectures demonstrate that the proposed token distillation mechanism can efficiently improve the accuracy. For example, the proposed STD boosts the top-1 accuracy of Mixer-S16 on ImageNet from 73.8% to 75.7% without any costly pre-training on JFT-300M. When applied to stronger architectures, e.g. CycleMLP-B1 and CycleMLP-B2, STD can still harvest about 1.1% and 0.5% accuracy gains, respectively.","url_abs":"https://proceedings.mlr.press/v162/li22c.html","url_pdf":"https://proceedings.mlr.press/v162/li22c/li22c.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":"spatial-channel-token-distillation-for-vision","repo_url":"https://github.com/devrimcavusoglu/std","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":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"mlp-mixer","method_name":"MLP-Mixer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"std","method_name":"STD"}],"datasets_introduced":[],"methods_introduced":[{"slug":"std","name":"STD","full_name":"Spatial-Channel Token Distillation"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResMLP-B24 + STD","rank_in_archive_order":544,"of":1060,"metrics":{"GFLOPs":"24.1","Number of params":"122.6M","Top 1 Accuracy":"82.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CycleMLP-B2 + STD","rank_in_archive_order":577,"of":1060,"metrics":{"GFLOPs":"4.0","Number of params":"30.1M","Top 1 Accuracy":"82.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Mixer-S16 + STD","rank_in_archive_order":940,"of":1060,"metrics":{"GFLOPs":"4.3","Number of params":"22.2M","Top 1 Accuracy":"75.7%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"devrimcavusoglu/std","kind":"listed","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":"ffb20345289ff9a49f023e06bb8f04ee73409ec12318e6a6bbdeaf532b81192d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}