000145637 001__ 145637 000145637 005__ 20200925153944.0 000145637 037__ $$aDZNE-2020-00967 000145637 041__ $$aEnglish 000145637 1001_ $$0P:(DE-2719)2812477$$aConjeti, Sailesh$$b0$$udzne 000145637 1112_ $$aMICCAI 2018$$cGranada$$d2018-09-16 - 2018-09-16$$wSpain 000145637 245__ $$aWebly Supervised Learning for Skin Lesion Classification 000145637 260__ $$c2018 000145637 3367_ $$033$$2EndNote$$aConference Paper 000145637 3367_ $$2DataCite$$aOther 000145637 3367_ $$2BibTeX$$aINPROCEEDINGS 000145637 3367_ $$2DRIVER$$aconferenceObject 000145637 3367_ $$2ORCID$$aLECTURE_SPEECH 000145637 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1597406579_15933$$xOther 000145637 520__ $$aWithin medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available web data through web-crawling. To handle noise and weak nature of web annotations, we propose a two-step transfer learning based training process with a robust loss function, termed as Webly Supervised Learning (WSL) to train deep models for the task. We also leverage search by image to improve the search specificity of our web-crawling and reduce cross-domain noise. Within WSL, we explicitly model the noise structure between classes and incorporate it to selectively distill knowledge from the web data during model training. To demonstrate improved performance due to WSL, we benchmarked on a publicly available 10-class fine-grained skin lesion classification dataset and report a significant improvement of top-1 classification accuracy from 71.25% to 80.53% due to the incorporation of web-supervision. 000145637 536__ $$0G:(DE-HGF)POF3-345$$a345 - Population Studies and Genetics (POF3-345)$$cPOF3-345$$fPOF III$$x0 000145637 8564_ $$uhttps://link.springer.com/chapter/10.1007/978-3-030-00934-2_45 000145637 909CO $$ooai:pub.dzne.de:145637$$pVDB 000145637 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812477$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b0$$kDZNE 000145637 9131_ $$0G:(DE-HGF)POF3-345$$1G:(DE-HGF)POF3-340$$2G:(DE-HGF)POF3-300$$aDE-HGF$$bForschungsbereich Gesundheit$$lErkrankungen des Nervensystems$$vPopulation Studies and Genetics$$x0 000145637 9141_ $$y2018 000145637 9201_ $$0I:(DE-2719)1040310$$kAG Reuter$$lImage Analysis$$x0 000145637 980__ $$aconf 000145637 980__ $$aVDB 000145637 980__ $$aI:(DE-2719)1040310 000145637 980__ $$aUNRESTRICTED