{"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/discrete-representations-strengthen-vision-1","title":"Discrete Representations Strengthen Vision Transformer Robustness","arxiv_id":"2111.10493","date":"2021-11-20","proceeding":"ICLR 2022 4","authors":["Chengzhi Mao","Lu Jiang","Mostafa Dehghani","Carl Vondrick","Rahul Sukthankar","Irfan Essa"],"abstract":"Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on ImageNet are overly reliant on local textures and fail to make adequate use of shape information. ViTs thus have difficulties generalizing to out-of-distribution, real-world data. To address this deficiency, we present a simple and effective architecture modification to ViT's input layer by adding discrete tokens produced by a vector-quantized encoder. Different from the standard continuous pixel tokens, discrete tokens are invariant under small perturbations and contain less information individually, which promote ViTs to learn global information that is invariant. Experimental results demonstrate that adding discrete representation on four architecture variants strengthens ViT robustness by up to 12% across seven ImageNet robustness benchmarks while maintaining the performance on ImageNet.","url_abs":"https://arxiv.org/abs/2111.10493v2","url_pdf":"https://arxiv.org/pdf/2111.10493v2.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":"discrete-representations-strengthen-vision-1","repo_url":"https://github.com/alibaba/easyrobust/tree/main/examples/imageclassification/imagenet/drvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-classification","task_name":"Image Classification"}],"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":"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":"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/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"DiscreteViT (Im21k)","rank_in_archive_order":11,"of":47,"metrics":{"Number of params":"87M","mean Corruption Error (mCE)":"38.74"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"DrViT","rank_in_archive_order":21,"of":47,"metrics":{"mean Corruption Error (mCE)":"46.22"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"DiscreteViT","rank_in_archive_order":22,"of":47,"metrics":{"Number of params":"87M","mean Corruption Error (mCE)":"46.22"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"DiscreteViT","rank_in_archive_order":20,"of":39,"metrics":{"Top-1 Error Rate":"44.74"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"DrViT","rank_in_archive_order":16,"of":20,"metrics":{"Top-1 accuracy":"44.72"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-stylized-imagenet","task":"Domain Generalization","dataset":"Stylized-ImageNet","model":"DiscreteViT","rank_in_archive_order":3,"of":3,"metrics":{"Top 1 Accuracy":"22.19"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DiscreteViT","rank_in_archive_order":262,"of":1060,"metrics":{"Top 1 Accuracy":"85.07%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"ViT-B (Discrete 512x512)","rank_in_archive_order":35,"of":106,"metrics":{"Top-1 Accuracy":"46.62"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.10493","atlas_url":"https://app.syntology.ai/?focus=2111.10493","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":"2111.10493"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.10493\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.10493"},"call":"get_concepts_for_paper(arxiv_id=\"2111.10493\")"}],"by_repo":[{"repo":"alibaba/easyrobust","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2209.07735"],"harvested_for_calls":[{"arxiv_id":"2209.07735","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2209.07735"},"call":"get_harvested_code_for_paper(arxiv_id=\"2209.07735\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"0cdeb085140671e1bebe871ae4fa302ec2ef5f233a85f184096eec950ba45d43","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}