{"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/fishnet-a-versatile-backbone-for-image-region","title":"FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction","arxiv_id":"1901.03495","date":"2019-01-11","proceeding":"NeurIPS 2018 12","authors":["Shuyang Sun","Jiangmiao Pang","Jianping Shi","Shuai Yi","Wanli Ouyang"],"abstract":"The basic principles in designing convolutional neural network (CNN)\nstructures for predicting objects on different levels, e.g., image-level,\nregion-level, and pixel-level are diverging. Generally, network structures\ndesigned specifically for image classification are directly used as default\nbackbone structure for other tasks including detection and segmentation, but\nthere is seldom backbone structure designed under the consideration of unifying\nthe advantages of networks designed for pixel-level or region-level predicting\ntasks, which may require very deep features with high resolution. Towards this\ngoal, we design a fish-like network, called FishNet. In FishNet, the\ninformation of all resolutions is preserved and refined for the final task.\nBesides, we observe that existing works still cannot \\emph{directly} propagate\nthe gradient information from deep layers to shallow layers. Our design can\nbetter handle this problem. Extensive experiments have been conducted to\ndemonstrate the remarkable performance of the FishNet. In particular, on\nImageNet-1k, the accuracy of FishNet is able to surpass the performance of\nDenseNet and ResNet with fewer parameters. FishNet was applied as one of the\nmodules in the winning entry of the COCO Detection 2018 challenge. The code is\navailable at https://github.com/kevin-ssy/FishNet.","url_abs":"http://arxiv.org/abs/1901.03495v1","url_pdf":"http://arxiv.org/pdf/1901.03495v1.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":"fishnet-a-versatile-backbone-for-image-region","repo_url":"https://github.com/kevin-ssy/FishNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fishnet-a-versatile-backbone-for-image-region","repo_url":"https://github.com/Mind23-2/MindCode-47","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"fishnet-a-versatile-backbone-for-image-region","repo_url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/fishnet99","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"fishnet-a-versatile-backbone-for-image-region","repo_url":"https://github.com/MindSpore-paper-code-3/code7/tree/main/fishnet99","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"fishnet-a-versatile-backbone-for-image-region","repo_url":"https://github.com/lyqcom/fishnet99","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fishnet-a-versatile-backbone-for-image-region","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"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":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.03495","atlas_url":"https://app.syntology.ai/?focus=1901.03495","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":"1901.03495"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1901.03495\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1901.03495"},"call":"get_concepts_for_paper(arxiv_id=\"1901.03495\")"}],"by_repo":[{"repo":"kevin-ssy/FishNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Mind23-2/MindCode-47","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-paper-code-3/code4","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-paper-code-3/code7","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lyqcom/fishnet99","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"osmr/imgclsmob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.08955"],"harvested_for_calls":[{"arxiv_id":"2004.08955","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.08955"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.08955\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"da2401384d682e8bb7fa7e6b79678c273c3cfea8f76e2df31421ee9238df8703","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}