{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:15:18Z","timestamp":1758273318310},"reference-count":14,"publisher":"Association for Computing Machinery (ACM)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>In this demonstration, we present Krypton, a system for accelerating occlusion-based deep convolution neural network (CNN) explanation workloads. Driven by the success of CNNs in image understanding tasks, there is growing adoption of CNNs in various domains, including high stakes applications such as radiology. However, users of such applications often seek an \"explanation\" for why a CNN predicted a certain label. One of the most widely used approaches for explaining CNN predictions is the occlusion-based explanation (OBE) method. This approach is computationally expensive due to the large number of re-inference requests produced. Krypton reduces the runtime of OBE by up to 35x by enabling incremental and approximate inference optimizations that are inspired by classical database query optimization techniques. We allow the audience to interactively diagnose CNN predictions from several use cases, including radiology and natural images. A short video of our demonstration can be found here: https:\/\/youtu.be\/1OWddbd4n6Y<\/jats:p>","DOI":"10.14778\/3352063.3352093","type":"journal-article","created":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T18:36:11Z","timestamp":1568831771000},"page":"1894-1897","source":"Crossref","is-referenced-by-count":6,"title":["Demonstration of Krypton"],"prefix":"10.14778","volume":"12","author":[{"given":"Allen","family":"Ordookhanians","sequence":"first","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Supun","family":"Nakandala","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,8]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Accessed","year":"2019"},{"key":"e_1_2_1_2_1","volume-title":"Accessed","year":"2019"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00051"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131885.3131906"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000020"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.7599\/hmr.2017.37.2.61"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"e_1_2_1_8_1","volume-title":"Explanation in artificial intelligence: Insights from the social sciences. arXiv preprint arXiv:1706.07269","author":"Miller T.","year":"2017"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/42201.42203"},{"key":"e_1_2_1_11_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034","author":"Simonyan K.","year":"2013"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3152676"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_1_14_1","volume-title":"Visualizing deep neural network decisions: Prediction difference analysis. arXiv preprint arXiv:1702.04595","author":"Zintgraf L. M.","year":"2017"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3352063.3352093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T10:32:35Z","timestamp":1672223555000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3352063.3352093"}},"subtitle":["optimized CNN inference for occlusion-based deep CNN explanations"],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":14,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["10.14778\/3352063.3352093"],"URL":"https:\/\/doi.org\/10.14778\/3352063.3352093","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}