{"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/understanding-gaussian-attention-bias-of","title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","arxiv_id":"2305.04722","date":"2023-05-08","proceeding":null,"authors":["Bum Jun Kim","Hyeyeon Choi","Hyeonah Jang","Sang Woo Kim"],"abstract":"Vision transformers (ViTs) that model an image as a sequence of partitioned patches have shown notable performance in diverse vision tasks. Because partitioning patches eliminates the image structure, to reflect the order of patches, ViTs utilize an explicit component called positional embedding. However, we claim that the use of positional embedding does not simply guarantee the order-awareness of ViT. To support this claim, we analyze the actual behavior of ViTs using an effective receptive field. We demonstrate that during training, ViT acquires an understanding of patch order from the positional embedding that is trained to be a specific pattern. Based on this observation, we propose explicitly adding a Gaussian attention bias that guides the positional embedding to have the corresponding pattern from the beginning of training. We evaluated the influence of Gaussian attention bias on the performance of ViTs in several image classification, object detection, and semantic segmentation experiments. The results showed that proposed method not only facilitates ViTs to understand images but also boosts their performance on various datasets, including ImageNet, COCO 2017, and ADE20K.","url_abs":"https://arxiv.org/abs/2305.04722v1","url_pdf":"https://arxiv.org/pdf/2305.04722v1.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":"understanding-gaussian-attention-bias-of","repo_url":"https://github.com/kmbmjn/GaussianAttentionBias","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"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":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","task":"Fine-Grained Image Classification","dataset":"Caltech-101","model":"ViT-S/16 (RPE w/ GAB)","rank_in_archive_order":11,"of":18,"metrics":{"Top-1 Error Rate":"9.798%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford-1","task":"Fine-Grained Image Classification","dataset":"Stanford Dogs","model":"ViT-B/16 (RPE w/ GAB)","rank_in_archive_order":18,"of":24,"metrics":{"Accuracy":"90.185%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ViT-B/16 (RPE w/ GAB)","rank_in_archive_order":639,"of":1060,"metrics":{"Top 1 Accuracy":"81.484%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stanford-cars","task":"Image Classification","dataset":"Stanford Cars","model":"ViT-B/16 (RPE w/ GAB)","rank_in_archive_order":9,"of":24,"metrics":{"Accuracy":"93.743"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stanford-cars","task":"Image Classification","dataset":"Stanford Cars","model":"ViT-M/16 (RPE w/ GAB)","rank_in_archive_order":23,"of":24,"metrics":{"Accuracy":"83.89"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Swin-S (RPE w/ GAB)","rank_in_archive_order":108,"of":225,"metrics":{"box mAP":"48.23"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"Swin-S (RPE w/ GAB)","rank_in_archive_order":70,"of":95,"metrics":{"mIoU":"46.41"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.04722","atlas_url":"https://app.syntology.ai/?focus=2305.04722","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":"2305.04722"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.04722\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.04722"},"call":"get_concepts_for_paper(arxiv_id=\"2305.04722\")"}],"by_repo":[{"repo":"kmbmjn/GaussianAttentionBias","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":"0dddff70dc3bc7fe5d9cb979d12aad9c41a8635cced7b465b8282ab08b488866","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}