{"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/complex-wavelet-mutual-information-loss-a","title":"Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation","arxiv_id":"2502.00563","date":"2025-02-01","proceeding":null,"authors":["Renhao Lu"],"abstract":"Recent advancements in deep neural networks have significantly enhanced the performance of semantic segmentation. However, class imbalance and instance imbalance remain persistent challenges, where smaller instances and thin boundaries are often overshadowed by larger structures. To address the multiscale nature of segmented objects, various models have incorporated mechanisms such as spatial attention and feature pyramid networks. Despite these advancements, most loss functions are still primarily pixel-wise, while regional and boundary-focused loss functions often incur high computational costs or are restricted to small-scale regions. To address this limitation, we propose the complex wavelet mutual information (CWMI) loss, a novel loss function that leverages mutual information from subband images decomposed by a complex steerable pyramid. The complex steerable pyramid captures features across multiple orientations and preserves structural similarity across scales. Meanwhile, mutual information is well-suited to capturing high-dimensional directional features and offers greater noise robustness. Extensive experiments on diverse segmentation datasets demonstrate that CWMI loss achieves significant improvements in both pixel-wise accuracy and topological metrics compared to state-of-the-art methods, while introducing minimal computational overhead. Our code is available at https://github.com/lurenhaothu/CWMI","url_abs":"https://arxiv.org/abs/2502.00563v2","url_pdf":"https://arxiv.org/pdf/2502.00563v2.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":"complex-wavelet-mutual-information-loss-a","repo_url":"https://github.com/lurenhaothu/CWMI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.00563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00563"}},"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/lurenhaothu/CWMI","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"5c4faffe8c16f583","entry":"BCE_withClassBalance","repo":"lurenhaothu/CWMI","repo_kind":"official","path":"model/CWMI_loss/CWMI_loss.py","file_url":"https://github.com/lurenhaothu/CWMI/blob/HEAD/model/CWMI_loss/CWMI_loss.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":"5c4faffe8c16f583"}},{"code_sha256_prefix":"e4bfe862f6651233","entry":"ComplexSteerablePyramid","repo":"lurenhaothu/CWMI","repo_kind":"official","path":"model/CWMI_loss/CWMI_loss.py","file_url":"https://github.com/lurenhaothu/CWMI/blob/HEAD/model/CWMI_loss/CWMI_loss.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":"e4bfe862f6651233"}},{"code_sha256_prefix":"d0557cdbc19dc417","entry":"CWMI_loss","repo":"lurenhaothu/CWMI","repo_kind":"official","path":"model/CWMI_loss/CWMI_loss.py","file_url":"https://github.com/lurenhaothu/CWMI/blob/HEAD/model/CWMI_loss/CWMI_loss.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":"d0557cdbc19dc417"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}