{"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/190513549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","arxiv_id":"1905.13549","date":"2019-05-29","proceeding":"NeurIPS 2019 12","authors":["Haohan Wang","Songwei Ge","Eric P. Xing","Zachary C. Lipton"],"abstract":"Despite their renowned predictive power on i.i.d. data, convolutional neural networks are known to rely more on high-frequency patterns that humans deem superficial than on low-frequency patterns that agree better with intuitions about what constitutes category membership. This paper proposes a method for training robust convolutional networks by penalizing the predictive power of the local representations learned by earlier layers. Intuitively, our networks are forced to discard predictive signals such as color and texture that can be gleaned from local receptive fields and to rely instead on the global structures of the image. Across a battery of synthetic and benchmark domain adaptation tasks, our method confers improved generalization out of the domain. Also, to evaluate cross-domain transfer, we introduce ImageNet-Sketch, a new dataset consisting of sketch-like images, that matches the ImageNet classification validation set in categories and scale.","url_abs":"https://arxiv.org/abs/1905.13549v2","url_pdf":"https://arxiv.org/pdf/1905.13549v2.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":"190513549","repo_url":"https://github.com/HaohanWang/PAR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"190513549","repo_url":"https://github.com/HaohanWang/PAR_experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"190513549","repo_url":"https://github.com/HaohanWang/ImageNet-Sketch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190513549","repo_url":"https://github.com/guanqun-yang/reproducibility_challenge_neurips_2019","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[{"slug":"imagenet-sketch","name":"ImageNet-Sketch","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"PAR (Alexnet)","rank_in_archive_order":114,"of":133,"metrics":{"Average Accuracy":"72.08"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.13549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.13549"}},"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/HaohanWang/ImageNet-Sketch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guanqun-yang/reproducibility_challenge_neurips_2019","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HaohanWang/PAR","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HaohanWang/PAR_experiments","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":3,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"b7986f80f9e6657f","entry":"AlexNetCaffe_PAR","repo":"HaohanWang/PAR_experiments","repo_kind":"official","path":"JigenPAR/models/caffenet.py","file_url":"https://github.com/HaohanWang/PAR_experiments/blob/HEAD/JigenPAR/models/caffenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7986f80f9e6657f"}},{"code_sha256_prefix":"8a0f092050404d37","entry":"GradientReverse","repo":"guanqun-yang/reproducibility_challenge_neurips_2019","repo_kind":"listed","path":"exp1.py","file_url":"https://github.com/guanqun-yang/reproducibility_challenge_neurips_2019/blob/HEAD/exp1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a0f092050404d37"}},{"code_sha256_prefix":"df9a43d63af2a9c6","entry":"Id","repo":"HaohanWang/PAR_experiments","repo_kind":"official","path":"JigenPAR/models/caffenet.py","file_url":"https://github.com/HaohanWang/PAR_experiments/blob/HEAD/JigenPAR/models/caffenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df9a43d63af2a9c6"}},{"code_sha256_prefix":"a8b7019c5d6306ff","entry":"PAR","repo":"guanqun-yang/reproducibility_challenge_neurips_2019","repo_kind":"listed","path":"exp1.py","file_url":"https://github.com/guanqun-yang/reproducibility_challenge_neurips_2019/blob/HEAD/exp1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8b7019c5d6306ff"}},{"code_sha256_prefix":"b5becb520f35423a","entry":"grad_reverse","repo":"guanqun-yang/reproducibility_challenge_neurips_2019","repo_kind":"listed","path":"exp1.py","file_url":"https://github.com/guanqun-yang/reproducibility_challenge_neurips_2019/blob/HEAD/exp1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5becb520f35423a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}