{"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/equivariant-transformer-networks","title":"Equivariant Transformer Networks","arxiv_id":"1901.11399","date":"2019-01-25","proceeding":null,"authors":["Kai Sheng Tai","Peter Bailis","Gregory Valiant"],"abstract":"How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the robustness of models towards pre-defined continuous transformation groups. Through the use of specially-derived canonical coordinate systems, ETs incorporate functions that are equivariant by construction with respect to these transformations. We show empirically that ETs can be flexibly composed to improve model robustness towards more complicated transformation groups in several parameters. On a real-world image classification task, ETs improve the sample efficiency of ResNet classifiers, achieving relative improvements in error rate of up to 15% in the limited data regime while increasing model parameter count by less than 1%.","url_abs":"https://arxiv.org/abs/1901.11399v2","url_pdf":"https://arxiv.org/pdf/1901.11399v2.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":"equivariant-transformer-networks","repo_url":"https://github.com/stanford-futuredata/equivariant-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"equivariant-transformer-networks","repo_url":"https://github.com/julianroth/equivariant-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"equivariant-transformer-networks","repo_url":"https://github.com/siddhantmittal7/GroupTransformEquivariance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.11399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11399"}},"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/siddhantmittal7/GroupTransformEquivariance","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/julianroth/equivariant-transformers","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanford-futuredata/equivariant-transformers","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"6692d23a5f54d8ef","entry":"conv3x3","repo":"stanford-futuredata/equivariant-transformers","repo_kind":"official","path":"etn/networks.py","file_url":"https://github.com/stanford-futuredata/equivariant-transformers/blob/HEAD/etn/networks.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":"6692d23a5f54d8ef"}},{"code_sha256_prefix":"761b8adcc5ecff14","entry":"identity_grid","repo":"stanford-futuredata/equivariant-transformers","repo_kind":"official","path":"etn/coordinates.py","file_url":"https://github.com/stanford-futuredata/equivariant-transformers/blob/HEAD/etn/coordinates.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":"761b8adcc5ecff14"}},{"code_sha256_prefix":"dc65775b942e8083","entry":"logpolar_grid","repo":"stanford-futuredata/equivariant-transformers","repo_kind":"official","path":"etn/coordinates.py","file_url":"https://github.com/stanford-futuredata/equivariant-transformers/blob/HEAD/etn/coordinates.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":"dc65775b942e8083"}},{"code_sha256_prefix":"1c00f43eee1d06c6","entry":"polar_grid","repo":"stanford-futuredata/equivariant-transformers","repo_kind":"official","path":"etn/coordinates.py","file_url":"https://github.com/stanford-futuredata/equivariant-transformers/blob/HEAD/etn/coordinates.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":"1c00f43eee1d06c6"}},{"code_sha256_prefix":"1c97aece4991619c","entry":"projective","repo":"stanford-futuredata/equivariant-transformers","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/stanford-futuredata/equivariant-transformers/blob/HEAD/datasets.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":"1c97aece4991619c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}