{"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/revisiting-the-shape-bias-of-deep-learning","title":"Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification","arxiv_id":"2206.06466","date":"2022-06-13","proceeding":null,"authors":["Adriano Lucieri","Fabian Schmeisser","Christoph Peter Balada","Shoaib Ahmed Siddiqui","Andreas Dengel","Sheraz Ahmed"],"abstract":"It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the fundamental properties of human vision. The reliance on shape features is primarily expected to improve the robustness of these models under covariate shift. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images. Our analysis shows that different skin lesion datasets exhibit varying biases towards individual image features. Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation. This indicates that these features are still represented in the learnt embedding spaces of the models, but not used for classification. In addition, the spectral analysis of different datasets shows that in contrast to common visual recognition, dermoscopic skin lesion classification, by nature, is reliant on complex feature combinations beyond shape-bias. As a natural consequence, shifting away from the prevalent desire of shape-biasing models can even improve skin lesion classifiers in some cases.","url_abs":"https://arxiv.org/abs/2206.06466v1","url_pdf":"https://arxiv.org/pdf/2206.06466v1.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":"revisiting-the-shape-bias-of-deep-learning","repo_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"lesion-classification","task_name":"Lesion Classification"},{"task_slug":"skin-lesion-classification","task_name":"Skin Lesion Classification"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.06466","atlas_url":"https://app.syntology.ai/?focus=2206.06466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06466"}},"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/adriano-lucieri/shape-bias-in-dermoscopy","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"bdbe6961123f9359","entry":"af_apr_p","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/apr_p.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/apr_p.py","link_basis":"harvester_set","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":"bdbe6961123f9359"}},{"code_sha256_prefix":"b4474de4084245ed","entry":"get_normalization_values","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/dataset_selector.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/dataset_selector.py","link_basis":"harvester_set","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":"b4474de4084245ed"}},{"code_sha256_prefix":"fcd950ab41d649b5","entry":"loss_selector","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/loss_selector.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/loss_selector.py","link_basis":"harvester_set","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":"fcd950ab41d649b5"}},{"code_sha256_prefix":"21e329a5e8553c84","entry":"lr_schedule_selector","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/optimizer_selector.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/optimizer_selector.py","link_basis":"harvester_set","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":"21e329a5e8553c84"}},{"code_sha256_prefix":"45b7aa89ba7539ae","entry":"mix_data_rfft","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/apr_p.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/apr_p.py","link_basis":"harvester_set","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":"45b7aa89ba7539ae"}},{"code_sha256_prefix":"13d1279fae0d550b","entry":"mixed_apr_p","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/apr_p.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/apr_p.py","link_basis":"harvester_set","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":"13d1279fae0d550b"}},{"code_sha256_prefix":"b1a2c9994a3b15c3","entry":"optimizer_selector","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/optimizer_selector.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/optimizer_selector.py","link_basis":"harvester_set","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":"b1a2c9994a3b15c3"}},{"code_sha256_prefix":"a57eb3c95c04e23b","entry":"model_selector","repo":"adriano-lucieri/shape-bias-in-dermoscopy","repo_kind":"official","path":"src/modules/model_selector.py","file_url":"https://github.com/adriano-lucieri/shape-bias-in-dermoscopy/blob/HEAD/src/modules/model_selector.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":"a57eb3c95c04e23b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}