{"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/robust-and-generalizable-visual","title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","arxiv_id":"2007.13003","date":"2020-07-25","proceeding":"ICLR 2021 1","authors":["Zhenlin Xu","Deyi Liu","Junlin Yang","Colin Raffel","Marc Niethammer"],"abstract":"While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation. Random convolutions are approximately shape-preserving and may distort local textures. Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local textures. Therefore, we explore using outputs of multi-scale random convolutions as new images or mixing them with the original images during training. When applying a network trained with our approach to unseen domains, our method consistently improves the performance on domain generalization benchmarks and is scalable to ImageNet. In particular, in the challenging scenario of generalizing to the sketch domain in PACS and to ImageNet-Sketch, our method outperforms state-of-art methods by a large margin. More interestingly, our method can benefit downstream tasks by providing a more robust pretrained visual representation.","url_abs":"https://arxiv.org/abs/2007.13003v3","url_pdf":"https://arxiv.org/pdf/2007.13003v3.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":"robust-and-generalizable-visual","repo_url":"https://github.com/tourdeml/robust-representation-random-convolutions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-and-generalizable-visual","repo_url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-and-generalizable-visual","repo_url":"https://github.com/MindSpore-scientific-2/code-11/tree/main/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-and-generalizable-visual","repo_url":"https://github.com/MindSpore-scientific/code-11/tree/main/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-and-generalizable-visual","repo_url":"https://github.com/wildphoton/RandConv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"RC (Alexnet)","rank_in_archive_order":120,"of":133,"metrics":{"Average Accuracy":"70.53"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.13003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13003"}},"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/MindSpore-scientific-2/code-11/tree/main/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wildphoton/RandConv","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-11/tree/main/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tourdeml/robust-representation-random-convolutions","reach":null}],"summary":{"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"repositories":2}},"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":3,"samples":[{"code_sha256_prefix":"5d97086fdb97d182","entry":"MultiScaleRandConv2d","repo":"wildphoton/RandConv","repo_kind":"listed","path":"lib/networks/rand_conv.py","file_url":"https://github.com/wildphoton/RandConv/blob/HEAD/lib/networks/rand_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5d97086fdb97d182"}},{"code_sha256_prefix":"b49ddd06add45cb9","entry":"RandConv2d","repo":"wildphoton/RandConv","repo_kind":"listed","path":"lib/networks/rand_conv.py","file_url":"https://github.com/wildphoton/RandConv/blob/HEAD/lib/networks/rand_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b49ddd06add45cb9"}},{"code_sha256_prefix":"2d525ad60cbb4382","entry":"randconv","repo":"tourdeml/robust-representation-random-convolutions","repo_kind":"listed","path":"randconv/randconv.py","file_url":"https://github.com/tourdeml/robust-representation-random-convolutions/blob/HEAD/randconv/randconv.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d525ad60cbb4382"}},{"code_sha256_prefix":"5fecd20400ccdedd","entry":"RandConvModule","repo":"wildphoton/RandConv","repo_kind":"listed","path":"lib/networks/rand_conv.py","file_url":"https://github.com/wildphoton/RandConv/blob/HEAD/lib/networks/rand_conv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5fecd20400ccdedd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}