{"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":"/method/bottleneck-transformer","slug":"bottleneck-transformer","name":"Bottleneck Transformer","full_name":"Bottleneck Transformer","full_name_withheld":false,"description_markdown":"The **Bottleneck Transformer (BoTNet) ** is an image classification model that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a [ResNet](https://paperswithcode.com/method/resnet) and no other changes, the approach improves upon baselines significantly on instance segmentation and object detection while also reducing the parameters, with minimal overhead in latency.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2101.11605v2","title":"Bottleneck Transformers for Visual Recognition","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Models","url":"/methods/category/image-models","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/robust-multimodal-survival-prediction-with","slug":"robust-multimodal-survival-prediction-with","title":"Robust Multimodal Survival Prediction with the Latent Differentiation Conditional Variational AutoEncoder","date":"2025-03-12","arxiv_id":"2503.09496","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["JJ-ZHOU-Code/RobustMultiModel"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"robust-multimodal-survival-prediction-with-1","title":"Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-scale-bottleneck-transformer-for-weakly","slug":"multi-scale-bottleneck-transformer-for-weakly","title":"Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection","date":"2024-05-08","arxiv_id":"2405.05130","n_code_links":1,"syntology":null},{"paper":null,"slug":"rock-classification-based-on-residual","title":"Rock Classification Based on Residual Networks","date":"2024-02-19","arxiv_id":"2402.11831","n_code_links":0,"syntology":null},{"paper":"/paper/svfap-self-supervised-video-facial-affect","slug":"svfap-self-supervised-video-facial-affect","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","date":"2023-12-31","arxiv_id":"2401.00416","n_code_links":1,"syntology":null},{"paper":"/paper/learning-bottleneck-transformer-for-event","slug":"learning-bottleneck-transformer-for-event","title":"Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification","date":"2023-08-23","arxiv_id":"2308.11937","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["event-ahu/efv_event_classification"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"marine-debris-detection-in-satellite","title":"Marine Debris Detection in Satellite Surveillance using Attention Mechanisms","date":"2023-07-09","arxiv_id":"2307.04128","n_code_links":0,"syntology":null},{"paper":null,"slug":"omnihorizon-in-the-wild-outdoors-depth-and","title":"Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding","date":"2022-12-09","arxiv_id":"2212.05040","n_code_links":0,"syntology":null},{"paper":"/paper/anatomy-guided-parallel-bottleneck","slug":"anatomy-guided-parallel-bottleneck","title":"AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy","date":"2021-05-02","arxiv_id":"2105.00381","n_code_links":1,"syntology":null},{"paper":"/paper/bottleneck-transformers-for-visual","slug":"bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","arxiv_id":"2101.11605","n_code_links":13,"syntology":{"ran":26,"of":49,"n_ran_checked":19,"n_instrument":7,"unverified":23,"pointer_only":8,"phrase":"26 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 23 unverified","official":null}}],"papers_shown":10,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":10,"with_a_code_link":6,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/bottleneck-transformer/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/bottleneck-transformer/papers/ran/1","json":"/method/bottleneck-transformer/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/survival-prediction","name":"Survival Prediction","papers":2},{"task":"/task/whole-slide-images","name":"whole slide images","papers":2},{"task":"/task/anatomy","name":"Anatomy","papers":1},{"task":"/task/anomaly-detection-in-surveillance-videos","name":"Anomaly Detection In Surveillance Videos","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/dynamic-facial-expression-recognition","name":"Dynamic Facial Expression Recognition","papers":1},{"task":"/task/emotion-recognition","name":"Emotion Recognition","papers":1},{"task":"/task/facial-expression-recognition-1","name":"Facial Expression Recognition","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":1},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1}],"tasks_shown":20,"n_tasks":23,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":1},{"year":"2023","papers":3},{"year":"2024","papers":2},{"year":"2025","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/bottleneck-transformer"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Bottleneck%20Transformer","read_at":"2026-10-05T00:53:14+00:00","query":"Bottleneck Transformer","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Bottleneck Transformer' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Bottleneck Transformer-Based Approach","Information Bottleneck-Guided Adaptive HyperGraph Transformer (IBAHGT)","Transformer","G-Transformer","L-Transformer","DT-Transformer","UQ-Transformer","OR-Transformer"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"62b52ef567700ceb7fcd5567ae7e2ba37c2dd59a28f847c22e117301a104503d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}