{"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/borrowing-treasures-from-the-wealthy-deep","title":"Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning","arxiv_id":"1702.08690","date":"2017-02-28","proceeding":"CVPR 2017 7","authors":["Weifeng Ge","Yizhou Yu"],"abstract":"Deep neural networks require a large amount of labeled training data during\nsupervised learning. However, collecting and labeling so much data might be\ninfeasible in many cases. In this paper, we introduce a source-target selective\njoint fine-tuning scheme for improving the performance of deep learning tasks\nwith insufficient training data. In this scheme, a target learning task with\ninsufficient training data is carried out simultaneously with another source\nlearning task with abundant training data. However, the source learning task\ndoes not use all existing training data. Our core idea is to identify and use a\nsubset of training images from the original source learning task whose\nlow-level characteristics are similar to those from the target learning task,\nand jointly fine-tune shared convolutional layers for both tasks. Specifically,\nwe compute descriptors from linear or nonlinear filter bank responses on\ntraining images from both tasks, and use such descriptors to search for a\ndesired subset of training samples for the source learning task.\n  Experiments demonstrate that our selective joint fine-tuning scheme achieves\nstate-of-the-art performance on multiple visual classification tasks with\ninsufficient training data for deep learning. Such tasks include Caltech 256,\nMIT Indoor 67, Oxford Flowers 102 and Stanford Dogs 120. In comparison to\nfine-tuning without a source domain, the proposed method can improve the\nclassification accuracy by 2% - 10% using a single model.","url_abs":"http://arxiv.org/abs/1702.08690v2","url_pdf":"http://arxiv.org/pdf/1702.08690v2.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":"borrowing-treasures-from-the-wealthy-deep","repo_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.08690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.08690"}},"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/ZYYSzj/Selective-Joint-Fine-tuning","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"61cfa43a945cbe3b","entry":"array_to_blobproto","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/io.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/io.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"61cfa43a945cbe3b"}},{"code_sha256_prefix":"6b3d943a10eb2014","entry":"arraylist_to_blobprotovector_str","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/io.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/io.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6b3d943a10eb2014"}},{"code_sha256_prefix":"093b959c347fd2f5","entry":"blobproto_to_array","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/io.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/io.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"093b959c347fd2f5"}},{"code_sha256_prefix":"a847938e3819a686","entry":"choose_color_by_layertype","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/draw.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/draw.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a847938e3819a686"}},{"code_sha256_prefix":"fc3a459b0c468f41","entry":"conv_params","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/coord_map.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/coord_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fc3a459b0c468f41"}},{"code_sha256_prefix":"c85f4a53630aa36a","entry":"coord_map","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/coord_map.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/coord_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c85f4a53630aa36a"}},{"code_sha256_prefix":"e8a3c25030f4c88c","entry":"crop_params","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/coord_map.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/coord_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e8a3c25030f4c88c"}},{"code_sha256_prefix":"2876e38623f7acbc","entry":"get_edge_label","repo":"ZYYSzj/Selective-Joint-Fine-tuning","repo_kind":"official","path":"caffe_zyyszj/python/caffe/draw.py","file_url":"https://github.com/ZYYSzj/Selective-Joint-Fine-tuning/blob/HEAD/caffe_zyyszj/python/caffe/draw.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2876e38623f7acbc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}