{"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-to-navigate-for-fine-grained","title":"Learning to Navigate for Fine-grained Classification","arxiv_id":"1809.00287","date":"2018-09-02","proceeding":"ECCV 2018 9","authors":["Ze Yang","Tiange Luo","Dong Wang","Zhiqiang Hu","Jun Gao","Li-Wei Wang"],"abstract":"Fine-grained classification is challenging due to the difficulty of finding\ndiscriminative features. Finding those subtle traits that fully characterize\nthe object is not straightforward. To handle this circumstance, we propose a\nnovel self-supervision mechanism to effectively localize informative regions\nwithout the need of bounding-box/part annotations. Our model, termed NTS-Net\nfor Navigator-Teacher-Scrutinizer Network, consists of a Navigator agent, a\nTeacher agent and a Scrutinizer agent. In consideration of intrinsic\nconsistency between informativeness of the regions and their probability being\nground-truth class, we design a novel training paradigm, which enables\nNavigator to detect most informative regions under the guidance from Teacher.\nAfter that, the Scrutinizer scrutinizes the proposed regions from Navigator and\nmakes predictions. Our model can be viewed as a multi-agent cooperation,\nwherein agents benefit from each other, and make progress together. NTS-Net can\nbe trained end-to-end, while provides accurate fine-grained classification\npredictions as well as highly informative regions during inference. We achieve\nstate-of-the-art performance in extensive benchmark datasets.","url_abs":"http://arxiv.org/abs/1809.00287v1","url_pdf":"http://arxiv.org/pdf/1809.00287v1.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-to-navigate-for-fine-grained","repo_url":"https://github.com/yangze0930/NTS-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/Mind23-2/MindCode-60","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/carlfu127/Keras-NTS-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/ntsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/CV51GO/FishNet_Megengine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/MS-Mind/MS-Code-06/tree/main/ntsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ntsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/code-implementation1/Code6/tree/main/ntsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ntsnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/nicolalandro/ntsnet-cub200","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-navigate-for-fine-grained","repo_url":"https://github.com/wwhio/megmodels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"informativeness","task_name":"Informativeness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"NTS-Net (K=4)","rank_in_archive_order":46,"of":57,"metrics":{"Accuracy":"91.4%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"NTS-Net (K=4)","rank_in_archive_order":57,"of":83,"metrics":{"Accuracy":"93.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00287"}},"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/yangze0930/NTS-Net","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicolalandro/ntsnet-cub200","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/carlfu127/Keras-NTS-Net","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-60","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code6/tree/main/ntsnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/ntsnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ntsnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/ntsnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CV51GO/FishNet_Megengine","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ntsnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wwhio/megmodels","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":3,"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1},"listed":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"yangze0930/NTS-Net","repo_kind":"official","path":"core/resnet.py","file_url":"https://github.com/yangze0930/NTS-Net/blob/HEAD/core/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"8d7ec010c29e813b","entry":"format_time","repo":"yangze0930/NTS-Net","repo_kind":"official","path":"core/utils.py","file_url":"https://github.com/yangze0930/NTS-Net/blob/HEAD/core/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d7ec010c29e813b"}},{"code_sha256_prefix":"baa6ed537245246b","entry":"hard_nms","repo":"nicolalandro/ntsnet-cub200","repo_kind":"listed","path":"nts_net/anchors.py","file_url":"https://github.com/nicolalandro/ntsnet-cub200/blob/HEAD/nts_net/anchors.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baa6ed537245246b"}},{"code_sha256_prefix":"6e643fa41475d0a4","entry":"init_log","repo":"yangze0930/NTS-Net","repo_kind":"official","path":"core/utils.py","file_url":"https://github.com/yangze0930/NTS-Net/blob/HEAD/core/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e643fa41475d0a4"}},{"code_sha256_prefix":"fd2341348e67f368","entry":"list_loss","repo":"yangze0930/NTS-Net","repo_kind":"official","path":"core/model.py","file_url":"https://github.com/yangze0930/NTS-Net/blob/HEAD/core/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd2341348e67f368"}},{"code_sha256_prefix":"7cbf9eb1d51ea71f","entry":"resnet18","repo":"yangze0930/NTS-Net","repo_kind":"official","path":"core/resnet.py","file_url":"https://github.com/yangze0930/NTS-Net/blob/HEAD/core/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7cbf9eb1d51ea71f"}},{"code_sha256_prefix":"e2c84ea74feab62d","entry":"resnet18","repo":"nicolalandro/ntsnet-cub200","repo_kind":"listed","path":"nts_net/resnet.py","file_url":"https://github.com/nicolalandro/ntsnet-cub200/blob/HEAD/nts_net/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2c84ea74feab62d"}},{"code_sha256_prefix":"fd5b7d49b4afca60","entry":"resnet34","repo":"yangze0930/NTS-Net","repo_kind":"official","path":"core/resnet.py","file_url":"https://github.com/yangze0930/NTS-Net/blob/HEAD/core/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd5b7d49b4afca60"}},{"code_sha256_prefix":"d3b306357c2242a1","entry":"resnet34","repo":"nicolalandro/ntsnet-cub200","repo_kind":"listed","path":"nts_net/resnet.py","file_url":"https://github.com/nicolalandro/ntsnet-cub200/blob/HEAD/nts_net/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3b306357c2242a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}