{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/dssd-deconvolutional-single-shot-detector","title":"DSSD : Deconvolutional Single Shot Detector","arxiv_id":"1701.06659","date":"2017-01-23","proceeding":null,"authors":["Cheng-Yang Fu","Wei Liu","Ananth Ranga","Ambrish Tyagi","Alexander C. Berg"],"abstract":"The main contribution of this paper is an approach for introducing additional\ncontext into state-of-the-art general object detection. To achieve this we\nfirst combine a state-of-the-art classifier (Residual-101[14]) with a fast\ndetection framework (SSD[18]). We then augment SSD+Residual-101 with\ndeconvolution layers to introduce additional large-scale context in object\ndetection and improve accuracy, especially for small objects, calling our\nresulting system DSSD for deconvolutional single shot detector. While these two\ncontributions are easily described at a high-level, a naive implementation does\nnot succeed. Instead we show that carefully adding additional stages of learned\ntransformations, specifically a module for feed-forward connections in\ndeconvolution and a new output module, enables this new approach and forms a\npotential way forward for further detection research. Results are shown on both\nPASCAL VOC and COCO detection. Our DSSD with $513 \\times 513$ input achieves\n81.5% mAP on VOC2007 test, 80.0% mAP on VOC2012 test, and 33.2% mAP on COCO,\noutperforming a state-of-the-art method R-FCN[3] on each dataset.","url_abs":"http://arxiv.org/abs/1701.06659v1","url_pdf":"http://arxiv.org/pdf/1701.06659v1.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":"dssd-deconvolutional-single-shot-detector","repo_url":"https://github.com/MTCloudVision/mxnet-dssd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":null},{"paper_slug":"dssd-deconvolutional-single-shot-detector","repo_url":"https://github.com/zzhuolun/IRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dssd-deconvolutional-single-shot-detector","repo_url":"https://github.com/yangyucheng000/Papers/tree/main/DSSH","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.06659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.06659"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/Papers/tree/main/DSSH","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MTCloudVision/mxnet-dssd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzhuolun/IRL","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"15a7ff98a54a906e","entry":"get_config","repo":"MTCloudVision/mxnet-dssd","repo_kind":"listed","path":"symbol/symbol_factory.py","file_url":"https://github.com/MTCloudVision/mxnet-dssd/blob/HEAD/symbol/symbol_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"15a7ff98a54a906e"}},{"code_sha256_prefix":"afcf00c13c576215","entry":"get_scales","repo":"MTCloudVision/mxnet-dssd","repo_kind":"listed","path":"symbol/symbol_factory.py","file_url":"https://github.com/MTCloudVision/mxnet-dssd/blob/HEAD/symbol/symbol_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"afcf00c13c576215"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}