{"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/dense-steerable-filter-cnns-for-exploiting","title":"Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images","arxiv_id":"2004.03037","date":"2020-04-06","proceeding":null,"authors":["Simon Graham","David Epstein","Nasir Rajpoot"],"abstract":"Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear. However, this rotational symmetry is not widely utilised as prior knowledge in modern Convolutional Neural Networks (CNNs), resulting in data hungry models that learn independent features at each orientation. Allowing CNNs to be rotation-equivariant removes the necessity to learn this set of transformations from the data and instead frees up model capacity, allowing more discriminative features to be learned. This reduction in the number of required parameters also reduces the risk of overfitting. In this paper, we propose Dense Steerable Filter CNNs (DSF-CNNs) that use group convolutions with multiple rotated copies of each filter in a densely connected framework. Each filter is defined as a linear combination of steerable basis filters, enabling exact rotation and decreasing the number of trainable parameters compared to standard filters. We also provide the first in-depth comparison of different rotation-equivariant CNNs for histology image analysis and demonstrate the advantage of encoding rotational symmetry into modern architectures. We show that DSF-CNNs achieve state-of-the-art performance, with significantly fewer parameters, when applied to three different tasks in the area of computational pathology: breast tumour classification, colon gland segmentation and multi-tissue nuclear segmentation.","url_abs":"https://arxiv.org/abs/2004.03037v2","url_pdf":"https://arxiv.org/pdf/2004.03037v2.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":"dense-steerable-filter-cnns-for-exploiting","repo_url":"https://github.com/simongraham/dsf-cnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dense-steerable-filter-cnns-for-exploiting","repo_url":"https://github.com/ladislasl/CNN_invar_rot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"breast-tumour-classification","task_name":"Breast Tumour Classification"},{"task_slug":"colorectal-gland-segmentation","task_name":"Colorectal Gland Segmentation:"},{"task_slug":"multi-tissue-nucleus-segmentation","task_name":"Multi-tissue Nucleus Segmentation"},{"task_slug":"nuclear-segmentation","task_name":"Nuclear Segmentation"},{"task_slug":"tumour-classification","task_name":"Tumour Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/breast-tumour-classification-on-pcam","task":"Breast Tumour Classification","dataset":"PCam","model":"DSF-CNN (C8)","rank_in_archive_order":1,"of":16,"metrics":{"AUC":"0.975"},"uses_additional_data":false},{"leaderboard":"/sota/colorectal-gland-segmentation-on-crag","task":"Colorectal Gland Segmentation:","dataset":"CRAG","model":"DSF-CNN (C8)","rank_in_archive_order":2,"of":15,"metrics":{"Dice":"0.891","F1-score":"0.874","Hausdorff Distance (mm)":"138.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-tissue-nucleus-segmentation-on-kumar","task":"Multi-tissue Nucleus Segmentation","dataset":"Kumar","model":"DSF-CNN (C8)","rank_in_archive_order":2,"of":18,"metrics":{"Dice":"0.826","Hausdorff Distance (mm)":"60"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.03037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03037"}},"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/ladislasl/CNN_invar_rot","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simongraham/dsf-cnn","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"dcde16f6c5150570","entry":"get_best_chkpts","repo":"simongraham/dsf-cnn","repo_kind":"official","path":"src/infer.py","file_url":"https://github.com/simongraham/dsf-cnn/blob/HEAD/src/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcde16f6c5150570"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}