{"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/centroid-transformers-learning-to-abstract","title":"Centroid Transformers: Learning to Abstract with Attention","arxiv_id":"2102.08606","date":"2021-02-17","proceeding":null,"authors":["Lemeng Wu","Xingchao Liu","Qiang Liu"],"abstract":"Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise relations between the elements of the inputs, and modify the inputs by propagating information between input pairs. As a result, it maps inputs to N outputs and casts a quadratic $O(N^2)$ memory and time complexity. We propose centroid attention, a generalization of self-attention that maps N inputs to M outputs $(M\\leq N)$, such that the key information in the inputs are summarized in the smaller number of outputs (called centroids). We design centroid attention by amortizing the gradient descent update rule of a clustering objective function on the inputs, which reveals an underlying connection between attention and clustering. By compressing the inputs to the centroids, we extract the key information useful for prediction and also reduce the computation of the attention module and the subsequent layers. We apply our method to various applications, including abstractive text summarization, 3D vision, and image processing. Empirical results demonstrate the effectiveness of our method over the standard transformers.","url_abs":"https://arxiv.org/abs/2102.08606v2","url_pdf":"https://arxiv.org/pdf/2102.08606v2.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":[],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CentroidViT-S (arXiv, 2021-02)","rank_in_archive_order":676,"of":1060,"metrics":{"GFLOPs":"9.4","Number of params":"22.3M","Top 1 Accuracy":"80.9%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.08606","atlas_url":"https://app.syntology.ai/?focus=2102.08606","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":"2102.08606"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2102.08606\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2102.08606"},"call":"get_concepts_for_paper(arxiv_id=\"2102.08606\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"caf2fc36e674711bd10a2fc062a4fcefd5ba16dbae57aa2be742f9498e9c6f0b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}