{"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/relus-are-sufficient-for-learning-implicit","title":"ReLUs Are Sufficient for Learning Implicit Neural Representations","arxiv_id":"2406.02529","date":"2024-06-04","proceeding":null,"authors":["Joseph Shenouda","Yamin Zhou","Robert D. Nowak"],"abstract":"Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations (INRs). Inspired by second order B-spline wavelets, we incorporate a set of simple constraints to the ReLU neurons in each layer of a deep neural network (DNN) to remedy the spectral bias. This in turn enables its use for various INR tasks. Empirically, we demonstrate that, contrary to popular belief, one can learn state-of-the-art INRs based on a DNN composed of only ReLU neurons. Next, by leveraging recent theoretical works which characterize the kinds of functions ReLU neural networks learn, we provide a way to quantify the regularity of the learned function. This offers a principled approach to selecting the hyperparameters in INR architectures. We substantiate our claims through experiments in signal representation, super resolution, and computed tomography, demonstrating the versatility and effectiveness of our method. The code for all experiments can be found at https://github.com/joeshenouda/relu-inrs.","url_abs":"https://arxiv.org/abs/2406.02529v2","url_pdf":"https://arxiv.org/pdf/2406.02529v2.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":"relus-are-sufficient-for-learning-implicit","repo_url":"https://github.com/joeshenouda/relu-inrs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.02529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02529"}},"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/joeshenouda/relu-inrs","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"6993cad8937592ca","entry":"get_mgrid","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"exp_audio_sig.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/exp_audio_sig.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6993cad8937592ca"}},{"code_sha256_prefix":"393fa5aa9ed0cf1d","entry":"bspline_wavelet","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"modules/bspline_w.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/modules/bspline_w.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"393fa5aa9ed0cf1d"}},{"code_sha256_prefix":"432e64ee10a38168","entry":"normalize","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"modules/utils.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/modules/utils.py","link_basis":"harvester_set","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":"432e64ee10a38168"}},{"code_sha256_prefix":"8fe08ad12dc74655","entry":"psnr","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"modules/utils.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/modules/utils.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":"8fe08ad12dc74655"}},{"code_sha256_prefix":"26862f3485c6ee4e","entry":"rsnr","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"modules/utils.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/modules/utils.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":"26862f3485c6ee4e"}},{"code_sha256_prefix":"acc69a4fca2eab93","entry":"radon","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"modules/lin_inverse.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/modules/lin_inverse.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":"acc69a4fca2eab93"}},{"code_sha256_prefix":"99ff1691eba94bb2","entry":"train","repo":"joeshenouda/relu-inrs","repo_kind":"official","path":"exp_univariate_path_norms.py","file_url":"https://github.com/joeshenouda/relu-inrs/blob/HEAD/exp_univariate_path_norms.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":"99ff1691eba94bb2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}