{"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/spatial-attention-module-thundernet","slug":"spatial-attention-module-thundernet","name":"Spatial Attention Module (ThunderNet)","full_name":"Spatial Attention Module (ThunderNet)","full_name_withheld":false,"description_markdown":"**Spatial Attention Module (SAM)** is a feature extraction module for object detection used in [ThunderNet](https://paperswithcode.com/method/thundernet).\r\n\r\nThe ThunderNet SAM explicitly re-weights the feature map before RoI warping over the spatial dimensions. The key idea of SAM is to use the knowledge from [RPN](https://paperswithcode.com/method/rpn) to refine the feature distribution of the feature map. RPN is trained to recognize foreground regions under the supervision of ground truths. Therefore, the intermediate features in RPN can be used to distinguish foreground features from background features. SAM accepts two inputs: the intermediate feature map from RPN $\\mathcal{F}^{RPN}$ and the thin feature map from the [Context Enhancement Module](https://paperswithcode.com/method/context-enhancement-module) $\\mathcal{F}^{CEM}$. The output of SAM $\\mathcal{F}^{SAM}$ is defined as:\r\n\r\n$$ \\mathcal{F}^{SAM} = \\mathcal{F}^{CEM} * \\text{sigmoid}\\left(\\theta\\left(\\mathcal{F}^{RPN}\\right)\\right) $$\r\n\r\nHere $\\theta\\left(·\\right)$ is a dimension transformation to match the number of channels in both feature maps. The sigmoid function is used to constrain the values within $\\left[0, 1\\right]$. At last, $\\mathcal{F}^{CEM}$ is re-weighted by the generated feature map for better feature distribution. For computational efficiency, we simply apply a 1×1 [convolution](https://paperswithcode.com/method/convolution) as $\\theta\\left(·\\right)$, so the computational cost of CEM is negligible. The Figure to the right shows the structure of SAM. \r\n\r\nSAM has two functions. The first one is to refine the feature distribution by strengthening foreground features and suppressing background features. The second one is to stabilize the training of RPN as SAM enables extra gradient flow from [R-CNN](https://paperswithcode.com/method/r-cnn) subnet to RPN. As a result, RPN receives additional supervision from RCNN subnet, which helps the training of RPN.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ThunderNet: Towards Real-time Generic Object Detection","paper":"/paper/thundernet-towards-real-time-generic-object","first_author":"Zheng Qin","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/thundernet-towards-real-time-generic-object"},"source":{"url":"https://arxiv.org/abs/1903.11752v3","title":"ThunderNet: Towards Real-time Generic Object Detection","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/ouyanghuiyu/Thundernet_Pytorch/blob/ab66b733a39c9d1c60b5373f84f861d9627d8c20/lib/model/faster_rcnn/modules.py#L209","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Extractors","url":"/methods/category/feature-extractors","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":null,"slug":"real-time-egocentric-segmentation-for-video","title":"Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality","date":"2022-07-04","arxiv_id":"2207.01296","n_code_links":0,"syntology":null},{"paper":null,"slug":"egocentric-human-segmentation-for-mixed","title":"Egocentric Human Segmentation for Mixed Reality","date":"2020-05-25","arxiv_id":"2005.12074","n_code_links":0,"syntology":null},{"paper":null,"slug":"thundernet-towards-real-time-generic-object-1","title":"ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/thundernet-towards-real-time-generic-object","slug":"thundernet-towards-real-time-generic-object","title":"ThunderNet: Towards Real-time Generic Object Detection","date":"2019-03-28","arxiv_id":"1903.11752","n_code_links":3,"syntology":null}],"papers_shown":4,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":4,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/mixed-reality","name":"Mixed Reality","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/object","name":"Object","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2019","papers":2},{"year":"2020","papers":1},{"year":"2022","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/spatial-attention-module-thundernet"},"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=Spatial%20Attention%20Module%20%28ThunderNet%29","read_at":"2026-10-05T01:02:20+00:00","query":"Spatial Attention Module (ThunderNet)","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":"1903.11752","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 'Spatial Attention Module (ThunderNet)' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["geospatial attention","Future Spatial Attention (FSA)","Low-Rank Spatial Attention (LRSA)","Contextual Spatial Attention (CSA)","IB-inspired spatial attention module","SpatialFormer Target Attention (SFTA)","Advance Spatial Attention (ASA) module","Spatially Modulated Co-Attention (SMCA)"],"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":"2961d4d6274edc8337ec929f8219e401209f36307a7c0353b653244ae9108d00","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}