{"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-perception-through-equivariance","title":"Robust Perception through Equivariance","arxiv_id":"2212.06079","date":"2022-12-12","proceeding":null,"authors":["Chengzhi Mao","Lingyu Zhang","Abhishek Joshi","Junfeng Yang","Hao Wang","Carl Vondrick"],"abstract":"Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference. By introducing constraints at inference time, we can shift the burden of robustness from training to the inference algorithm, thereby allowing the model to adjust dynamically to each individual image's unique and potentially novel characteristics at inference time. Among different constraints, we find that equivariance-based constraints are most effective, because they allow dense constraints in the feature space without overly constraining the representation at a fine-grained level. Our theoretical results validate the importance of having such dense constraints at inference time. Our empirical experiments show that restoring feature equivariance at inference time defends against worst-case adversarial perturbations. The method obtains improved adversarial robustness on four datasets (ImageNet, Cityscapes, PASCAL VOC, and MS-COCO) on image recognition, semantic segmentation, and instance segmentation tasks. Project page is available at equi4robust.cs.columbia.edu.","url_abs":"https://arxiv.org/abs/2212.06079v2","url_pdf":"https://arxiv.org/pdf/2212.06079v2.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-perception-through-equivariance","repo_url":"https://github.com/cvlab-columbia/equi4rob","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.06079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.06079"}},"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":"deterministic:regex_extraction","url":"https://github.com/cvlab-columbia/Equi4Rob","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cvlab-columbia/equi4rob","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_honours":2,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"community":{"samples":3,"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":4,"samples":[{"code_sha256_prefix":"826cdccf35d36049","entry":"Equi_Score","repo":"cvlab-columbia/equi4rob","repo_kind":"official","path":"learning/sentive_loss.py","file_url":"https://github.com/cvlab-columbia/equi4rob/blob/HEAD/learning/sentive_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"826cdccf35d36049"}},{"code_sha256_prefix":"f0bead498d7b3068","entry":"get_rot_mat","repo":"cvlab-columbia/equi4rob","repo_kind":"official","path":"learning/sentive_loss.py","file_url":"https://github.com/cvlab-columbia/equi4rob/blob/HEAD/learning/sentive_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0bead498d7b3068"}},{"code_sha256_prefix":"0e0900a2734c87d4","entry":"norm2","repo":"cvlab-columbia/equi4rob","repo_kind":"official","path":"learning/sentive_loss.py","file_url":"https://github.com/cvlab-columbia/equi4rob/blob/HEAD/learning/sentive_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e0900a2734c87d4"}},{"code_sha256_prefix":"b37bff7437cdf965","entry":"rot_img","repo":"cvlab-columbia/equi4rob","repo_kind":"official","path":"learning/sentive_loss.py","file_url":"https://github.com/cvlab-columbia/equi4rob/blob/HEAD/learning/sentive_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b37bff7437cdf965"}},{"code_sha256_prefix":"a199e6993774728a","entry":"conv3x3","repo":"nayeemrizve/invariance-equivariance","repo_kind":"community","path":"models/resnet_inv_eq.py","file_url":"https://github.com/nayeemrizve/invariance-equivariance/blob/HEAD/models/resnet_inv_eq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a199e6993774728a"}},{"code_sha256_prefix":"5dfeaba4ac54fa20","entry":"resnet12","repo":"nayeemrizve/invariance-equivariance","repo_kind":"community","path":"models/resnet_inv_eq.py","file_url":"https://github.com/nayeemrizve/invariance-equivariance/blob/HEAD/models/resnet_inv_eq.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":"5dfeaba4ac54fa20"}},{"code_sha256_prefix":"6fdd80fca0bb0948","entry":"resnet18","repo":"nayeemrizve/invariance-equivariance","repo_kind":"community","path":"models/resnet_inv_eq.py","file_url":"https://github.com/nayeemrizve/invariance-equivariance/blob/HEAD/models/resnet_inv_eq.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":"6fdd80fca0bb0948"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}