{"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/deep-learning-on-implicit-neural-datasets","title":"Discretization Invariant Networks for Learning Maps between Neural Fields","arxiv_id":"2206.01178","date":"2022-06-02","proceeding":null,"authors":["Clinton J. Wang","Polina Golland"],"abstract":"With the emergence of powerful representations of continuous data in the form of neural fields, there is a need for discretization invariant learning: an approach for learning maps between functions on continuous domains without being sensitive to how the function is sampled. We present a new framework for understanding and designing discretization invariant neural networks (DI-Nets), which generalizes many discrete networks such as convolutional neural networks as well as continuous networks such as neural operators. Our analysis establishes upper bounds on the deviation in model outputs under different finite discretizations, and highlights the central role of point set discrepancy in characterizing such bounds. This insight leads to the design of a family of neural networks driven by numerical integration via quasi-Monte Carlo sampling with discretizations of low discrepancy. We prove by construction that DI-Nets universally approximate a large class of maps between integrable function spaces, and show that discretization invariance also describes backpropagation through such models. Applied to neural fields, convolutional DI-Nets can learn to classify and segment visual data under various discretizations, and sometimes generalize to new types of discretizations at test time. Code: https://github.com/clintonjwang/DI-net.","url_abs":"https://arxiv.org/abs/2206.01178v4","url_pdf":"https://arxiv.org/pdf/2206.01178v4.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":"deep-learning-on-implicit-neural-datasets","repo_url":"https://github.com/clintonjwang/di-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"numerical-integration","task_name":"Numerical Integration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.01178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01178"}},"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/clintonjwang/di-net","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"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":"33dfd14c28e8f4f4","entry":"Conv2","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/classifier.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/classifier.py","link_basis":"harvester_set","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":"33dfd14c28e8f4f4"}},{"code_sha256_prefix":"026bed8688ab8bca","entry":"Conv4","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/classifier.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/classifier.py","link_basis":"harvester_set","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":"026bed8688ab8bca"}},{"code_sha256_prefix":"43fb14fcef7c191d","entry":"conv3d_bn_relu","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/seg.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/seg.py","link_basis":"harvester_set","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":"43fb14fcef7c191d"}},{"code_sha256_prefix":"0deb0609b7cd252c","entry":"conv_bn_relu","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/classifier.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/classifier.py","link_basis":"harvester_set","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":"0deb0609b7cd252c"}},{"code_sha256_prefix":"1b0eed42d48ac4ef","entry":"decomposed_siren","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/hypernets.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/hypernets.py","link_basis":"harvester_set","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":"1b0eed42d48ac4ef"}},{"code_sha256_prefix":"c2bc0cbdf4022748","entry":"get_convnext_block","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/convnext.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/convnext.py","link_basis":"harvester_set","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":"c2bc0cbdf4022748"}},{"code_sha256_prefix":"f7e9c30ec4cad6e4","entry":"interpolate_gt_seg","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/experiments/segment.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/experiments/segment.py","link_basis":"harvester_set","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":"f7e9c30ec4cad6e4"}},{"code_sha256_prefix":"97416b45ddb6851c","entry":"to_seg_siren","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/hypernets.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/hypernets.py","link_basis":"harvester_set","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":"97416b45ddb6851c"}},{"code_sha256_prefix":"25c08cdc853c7c75","entry":"translate_convnext_block","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/convnext.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/convnext.py","link_basis":"harvester_set","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":"25c08cdc853c7c75"}},{"code_sha256_prefix":"490542f18fdb2fb4","entry":"vectorize_siren","repo":"clintonjwang/di-net","repo_kind":"official","path":"dinet/baselines/hypernets.py","file_url":"https://github.com/clintonjwang/di-net/blob/HEAD/dinet/baselines/hypernets.py","link_basis":"harvester_set","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":"490542f18fdb2fb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}