{"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/learning-deconvolution-network-for-semantic","title":"Learning Deconvolution Network for Semantic Segmentation","arxiv_id":"1505.04366","date":"2015-05-17","proceeding":"ICCV 2015 12","authors":["Hyeonwoo Noh","Seunghoon Hong","Bohyung Han"],"abstract":"We propose a novel semantic segmentation algorithm by learning a\ndeconvolution network. We learn the network on top of the convolutional layers\nadopted from VGG 16-layer net. The deconvolution network is composed of\ndeconvolution and unpooling layers, which identify pixel-wise class labels and\npredict segmentation masks. We apply the trained network to each proposal in an\ninput image, and construct the final semantic segmentation map by combining the\nresults from all proposals in a simple manner. The proposed algorithm mitigates\nthe limitations of the existing methods based on fully convolutional networks\nby integrating deep deconvolution network and proposal-wise prediction; our\nsegmentation method typically identifies detailed structures and handles\nobjects in multiple scales naturally. Our network demonstrates outstanding\nperformance in PASCAL VOC 2012 dataset, and we achieve the best accuracy\n(72.5%) among the methods trained with no external data through ensemble with\nthe fully convolutional network.","url_abs":"http://arxiv.org/abs/1505.04366v1","url_pdf":"http://arxiv.org/pdf/1505.04366v1.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":"learning-deconvolution-network-for-semantic","repo_url":"https://github.com/GoNgXiAoPeNg1/caffeBVLCplus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-deconvolution-network-for-semantic","repo_url":"https://github.com/HyeonwooNoh/DeconvNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-deconvolution-network-for-semantic","repo_url":"https://github.com/HyeonwooNoh/caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-deconvolution-network-for-semantic","repo_url":"https://github.com/arahusky/Tensorflow-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-deconvolution-network-for-semantic","repo_url":"https://github.com/baucheng/caffeFA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/curved-text-detection-on-scut-ctw1500","task":"Curved Text Detection","dataset":"SCUT-CTW1500","model":"CTD+TLOC [[Noh et al.(2015)Noh, Hong, and Han]]","rank_in_archive_order":4,"of":5,"metrics":{"F-Measure":"73.4%"},"uses_additional_data":false},{"leaderboard":"/sota/curved-text-detection-on-scut-ctw1500","task":"Curved Text Detection","dataset":"SCUT-CTW1500","model":"CTD [[Noh et al.(2015)Noh, Hong, and Han]]","rank_in_archive_order":5,"of":5,"metrics":{"F-Measure":"69.5%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.04366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.04366"}},"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/GoNgXiAoPeNg1/caffeBVLCplus","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arahusky/Tensorflow-Segmentation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HyeonwooNoh/DeconvNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HyeonwooNoh/caffe","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baucheng/caffeFA","reach":{"status":"unanswered"}}],"summary":{"ran_violates":1,"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"e7e0093cbca9d12f","entry":"download_image","repo":"HyeonwooNoh/caffe","repo_kind":"listed","path":"examples/finetune_flickr_style/assemble_data.py","file_url":"https://github.com/HyeonwooNoh/caffe/blob/HEAD/examples/finetune_flickr_style/assemble_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e7e0093cbca9d12f"}},{"code_sha256_prefix":"9bf5955c8ae6f932","entry":"draw_results","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"9bf5955c8ae6f932"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}