FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3156331882> ?p ?o ?g. }

• W3156331882 abstract "In supervised learning for medical image analysis, sample selection methodologies are fundamental to attain optimum system performance promptly and with minimal expert interactions (e.g. label querying in an active learning setup). In this paper we propose a novel sample selection methodology based on deep features leveraging information contained in interpretability saliency maps. In the absence of ground truth labels for informative samples, we use a novel self supervised learning based approach for training a classifier that learns to identify the most informative sample in a given batch of images. We demonstrate the benefits of the proposed approach, termed Interpretability-Driven Sample Selection (IDEAL), in an active learning setup aimed at lung disease classification and histopathology image segmentation. We analyze three different approaches to determine sample informativeness from interpretability saliency maps: (i) an observational model stemming from findings on previous uncertainty-based sample selection approaches, (ii) a radiomics-based model, and (iii) a novel data-driven self-supervised approach. We compare IDEAL to other baselines using the publicly available NIH chest X-ray dataset for lung disease classification, and a public histopathology segmentation dataset (GLaS), demonstrating the potential of using interpretability information for sample selection in active learning systems. Results show our proposed self supervised approach outperforms other approaches in selecting informative samples leading to state of the art performance with fewer samples." @default.
• W3156331882 created "2021-04-26" @default.
• W3156331882 creator A5078933997 @default.
• W3156331882 date "2021-04-13" @default.
• W3156331882 modified "2023-10-01" @default.
• W3156331882 title "Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation" @default.
• W3156331882 cites W105577636 @default.
• W3156331882 cites W132742163 @default.
• W3156331882 cites W1446751132 @default.
• W3156331882 cites W1481846563 @default.
• W3156331882 cites W1510433709 @default.
• W3156331882 cites W1513874326 @default.
• W3156331882 cites W1528361845 @default.
• W3156331882 cites W154299906 @default.
• W3156331882 cites W1571891713 @default.
• W3156331882 cites W1589990798 @default.
• W3156331882 cites W1607839974 @default.
• W3156331882 cites W1614433159 @default.
• W3156331882 cites W1901129140 @default.
• W3156331882 cites W1975672287 @default.
• W3156331882 cites W1983747079 @default.
• W3156331882 cites W1985727327 @default.
• W3156331882 cites W2005947232 @default.
• W3156331882 cites W2008548542 @default.
• W3156331882 cites W2016724224 @default.
• W3156331882 cites W2023327449 @default.
• W3156331882 cites W2025225790 @default.
• W3156331882 cites W2026526178 @default.
• W3156331882 cites W2041254384 @default.
• W3156331882 cites W2045405067 @default.
• W3156331882 cites W2049389369 @default.
• W3156331882 cites W2062704867 @default.
• W3156331882 cites W2065585442 @default.
• W3156331882 cites W2071353422 @default.
• W3156331882 cites W2078547101 @default.
• W3156331882 cites W2098742124 @default.
• W3156331882 cites W2100110706 @default.
• W3156331882 cites W2109849958 @default.
• W3156331882 cites W2116730809 @default.
• W3156331882 cites W2146994775 @default.
• W3156331882 cites W2150267693 @default.
• W3156331882 cites W2171671120 @default.
• W3156331882 cites W2194775991 @default.
• W3156331882 cites W2195388612 @default.
• W3156331882 cites W2197357114 @default.
• W3156331882 cites W2199926372 @default.
• W3156331882 cites W2286639964 @default.
• W3156331882 cites W2288892845 @default.
• W3156331882 cites W2295107390 @default.
• W3156331882 cites W2326925005 @default.
• W3156331882 cites W2346062110 @default.
• W3156331882 cites W24458637 @default.
• W3156331882 cites W2469004055 @default.
• W3156331882 cites W2499363926 @default.
• W3156331882 cites W2511730936 @default.
• W3156331882 cites W2513367050 @default.
• W3156331882 cites W2522391363 @default.
• W3156331882 cites W2525235915 @default.
• W3156331882 cites W2527062305 @default.
• W3156331882 cites W2531866780 @default.
• W3156331882 cites W2536210040 @default.
• W3156331882 cites W2559576743 @default.
• W3156331882 cites W2560510252 @default.
• W3156331882 cites W2565058889 @default.
• W3156331882 cites W25753666 @default.
• W3156331882 cites W2584907666 @default.
• W3156331882 cites W2593021375 @default.
• W3156331882 cites W2594475271 @default.
• W3156331882 cites W2597787948 @default.
• W3156331882 cites W2600383743 @default.
• W3156331882 cites W2605409611 @default.
• W3156331882 cites W2625559849 @default.
• W3156331882 cites W2711924351 @default.
• W3156331882 cites W2750729880 @default.
• W3156331882 cites W2753367315 @default.
• W3156331882 cites W2766485978 @default.
• W3156331882 cites W2767128594 @default.
• W3156331882 cites W2769440362 @default.
• W3156331882 cites W2770241596 @default.
• W3156331882 cites W2798976889 @default.
• W3156331882 cites W2799792660 @default.
• W3156331882 cites W2806695658 @default.
• W3156331882 cites W2884420041 @default.
• W3156331882 cites W2886049744 @default.
• W3156331882 cites W2888052345 @default.
• W3156331882 cites W2890103789 @default.
• W3156331882 cites W2890139949 @default.
• W3156331882 cites W2890858414 @default.
• W3156331882 cites W2898091194 @default.
• W3156331882 cites W2901354392 @default.
• W3156331882 cites W2904204744 @default.
• W3156331882 cites W2911928347 @default.
• W3156331882 cites W2913152967 @default.
• W3156331882 cites W2925134950 @default.
• W3156331882 cites W2926307165 @default.
• W3156331882 cites W2941567073 @default.
• W3156331882 cites W2955669510 @default.
• W3156331882 cites W2962824366 @default.
• W3156331882 cites W2962835968 @default.
• W3156331882 cites W2962851944 @default.

• next