{"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/truly-scale-equivariant-deep-nets-with-1","title":"Truly Scale-Equivariant Deep Nets with Fourier Layers","arxiv_id":"2311.02922","date":"2023-11-06","proceeding":"NeurIPS 2023 11","authors":["Md Ashiqur Rahman","Raymond A. Yeh"],"abstract":"In computer vision, models must be able to adapt to changes in image resolution to effectively carry out tasks such as image segmentation; This is known as scale-equivariance. Recent works have made progress in developing scale-equivariant convolutional neural networks, e.g., through weight-sharing and kernel resizing. However, these networks are not truly scale-equivariant in practice. Specifically, they do not consider anti-aliasing as they formulate the down-scaling operation in the continuous domain. To address this shortcoming, we directly formulate down-scaling in the discrete domain with consideration of anti-aliasing. We then propose a novel architecture based on Fourier layers to achieve truly scale-equivariant deep nets, i.e., absolute zero equivariance-error. Following prior works, we test this model on MNIST-scale and STL-10 datasets. Our proposed model achieves competitive classification performance while maintaining zero equivariance-error.","url_abs":"https://arxiv.org/abs/2311.02922v1","url_pdf":"https://arxiv.org/pdf/2311.02922v1.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":"truly-scale-equivariant-deep-nets-with-1","repo_url":"https://github.com/ashiq24/scale_equivarinat_fourier_layer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.02922","atlas_url":"https://app.syntology.ai/?focus=2311.02922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02922"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ashiq24/scale_equivarinat_fourier_layer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"62374d75a1d9baad","entry":"compl_mul1d","repo":"ashiq24/scale_equivarinat_fourier_layer","repo_kind":"official","path":"scale_eq/layers/spectral_conv.py","file_url":"https://github.com/ashiq24/scale_equivarinat_fourier_layer/blob/HEAD/scale_eq/layers/spectral_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62374d75a1d9baad"}},{"code_sha256_prefix":"b013152707edebc6","entry":"compl_mul2d","repo":"ashiq24/scale_equivarinat_fourier_layer","repo_kind":"official","path":"scale_eq/layers/spectral_conv.py","file_url":"https://github.com/ashiq24/scale_equivarinat_fourier_layer/blob/HEAD/scale_eq/layers/spectral_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b013152707edebc6"}},{"code_sha256_prefix":"7dd9d629200b2969","entry":"enblock2d","repo":"ashiq24/scale_equivarinat_fourier_layer","repo_kind":"official","path":"scale_eq/layers/complex_modules.py","file_url":"https://github.com/ashiq24/scale_equivarinat_fourier_layer/blob/HEAD/scale_eq/layers/complex_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7dd9d629200b2969"}},{"code_sha256_prefix":"99eb878348e6db46","entry":"get_block1d","repo":"ashiq24/scale_equivarinat_fourier_layer","repo_kind":"official","path":"scale_eq/layers/complex_modules.py","file_url":"https://github.com/ashiq24/scale_equivarinat_fourier_layer/blob/HEAD/scale_eq/layers/complex_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99eb878348e6db46"}},{"code_sha256_prefix":"19962b66c82619e6","entry":"get_block2d","repo":"ashiq24/scale_equivarinat_fourier_layer","repo_kind":"official","path":"scale_eq/layers/complex_modules.py","file_url":"https://github.com/ashiq24/scale_equivarinat_fourier_layer/blob/HEAD/scale_eq/layers/complex_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19962b66c82619e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}