{"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/thundernet-towards-real-time-generic-object","title":"ThunderNet: Towards Real-time Generic Object Detection","arxiv_id":"1903.11752","date":"2019-03-28","proceeding":null,"authors":["Zheng Qin","Zeming Li","Zhaoning Zhang","Yiping Bao","Gang Yu","Yuxing Peng","Jian Sun"],"abstract":"Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. However, previous CNN-based detectors suffer from enormous computational cost, which hinders them from real-time inference in computation-constrained scenarios. In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet. In the backbone part, we analyze the drawbacks in previous lightweight backbones and present a lightweight backbone designed for object detection. In the detection part, we exploit an extremely efficient RPN and detection head design. To generate more discriminative feature representation, we design two efficient architecture blocks, Context Enhancement Module and Spatial Attention Module. At last, we investigate the balance between the input resolution, the backbone, and the detection head. Compared with lightweight one-stage detectors, ThunderNet achieves superior performance with only 40% of the computational cost on PASCAL VOC and COCO benchmarks. Without bells and whistles, our model runs at 24.1 fps on an ARM-based device. To the best of our knowledge, this is the first real-time detector reported on ARM platforms. Our code and models are available at \\url{https://github.com/qinzheng93/ThunderNet}.","url_abs":"https://arxiv.org/abs/1903.11752v3","url_pdf":"https://arxiv.org/pdf/1903.11752v3.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":"thundernet-towards-real-time-generic-object","repo_url":"https://github.com/qinzheng93/thundernet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"thundernet-towards-real-time-generic-object","repo_url":"https://github.com/saswat0/Thundernet-Object-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"thundernet-towards-real-time-generic-object","repo_url":"https://github.com/ouyanghuiyu/Thundernet_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"context-enhancement-module","method_name":"Context Enhancement Module"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"ohem","method_name":"OHEM"},{"method_slug":"position-sensitive-roialign","method_name":"Position-Sensitive RoIAlign"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"snet","method_name":"SNet"},{"method_slug":"shufflenet-v2-block","method_name":"ShuffleNet V2 Block"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"soft-nms","method_name":"Soft-NMS"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-attention-module-thundernet","method_name":"Spatial Attention Module (ThunderNet)"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"thundernet","method_name":"ThunderNet"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"context-enhancement-module","name":"Context Enhancement Module","full_name":"Context Enhancement Module"},{"slug":"snet","name":"SNet","full_name":"SNet"},{"slug":"spatial-attention-module-thundernet","name":"Spatial Attention Module (ThunderNet)","full_name":"Spatial Attention Module (ThunderNet)"},{"slug":"thundernet","name":"ThunderNet","full_name":"ThunderNet"}],"results":[{"leaderboard":"/sota/object-detection-on-pascal-voc-2007","task":"Object Detection","dataset":"PASCAL VOC 2007","model":"ThunderNet SNet535 Backbone","rank_in_archive_order":16,"of":30,"metrics":{"MAP":"78.6%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.11752","atlas_url":"https://app.syntology.ai/?focus=1903.11752","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":"1903.11752"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.11752\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.11752"},"call":"get_concepts_for_paper(arxiv_id=\"1903.11752\")"}],"by_repo":[{"repo":"qinzheng93/thundernet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"saswat0/Thundernet-Object-Detection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ouyanghuiyu/Thundernet_Pytorch","kind":"listed","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":"af25d7219e1ee31146b5acd12a859a4a1441c95c86a441cbb064ed7c43e16167","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}