{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T21:42:40Z","timestamp":1784842960853,"version":"3.55.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685489","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"abstract":"<jats:p>Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have different emphases but are rather one-sided. They primarily analyse the attention mechanisms or gradient-based attribution while neglecting the magnitudes of input feature values or the skip-connection module. Moreover, they inevitably bring spurious noisy pixel attributions unrelated to the model\u2019s decision, hindering humans\u2019 trust in the spotted visualization result. Hence, we propose an easy-to-implement but effective way to remedy this flaw: Smooth Noise Norm Attention (SNNA). We weigh the attention by the norm of the transformed value vector and guide the label-specific signal with the attention gradient, then randomly sample the input perturbations and average the corresponding gradients to produce noise-free attribution. Instead of evaluating the explanation method on the binary or multi-class classification tasks like in previous works, we explore the more complex multi-label classification scenario in this work, i.e., the driving action prediction task, and trained a model for it specifically. Both qualitative and quantitative evaluation results show the superiority of SNNA compared to other SOTA attention-based explainable methods in generating a clearer visual explanation map and ranking the input pixel importance.<\/jats:p>","DOI":"10.3233\/faia240520","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:44:33Z","timestamp":1729169073000},"source":"Crossref","is-referenced-by-count":2,"title":["Noise-Free Explanation for Driving Action Prediction"],"prefix":"10.3233","author":[{"given":"Hongbo","family":"Zhu","sequence":"first","affiliation":[{"name":"Manchester Centre for Robotics and AI, University of Manchester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodor","family":"Wulff","sequence":"additional","affiliation":[{"name":"Manchester Centre for Robotics and AI, University of Manchester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul Singh","family":"Maharjan","sequence":"additional","affiliation":[{"name":"Manchester Centre for Robotics and AI, University of Manchester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinpei","family":"Han","sequence":"additional","affiliation":[{"name":"Brain & Behavior Lab, Department of Computing, Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelo","family":"Cangelosi","sequence":"additional","affiliation":[{"name":"Manchester Centre for Robotics and AI, University of Manchester"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:44:34Z","timestamp":1729169074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240520"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240520","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}