{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T09:49:03Z","timestamp":1747216143294,"version":"3.40.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"type":"electronic","value":"9781643685489"}],"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>Recently, it has been shown that simulating computations in early primate visual areas, up to the primary visual cortex (V1), at the front of convolutional neural networks (CNNs) leads to improvements in robustness to image corruptions. However, it remains unclear whether this improvement requires precisely matching the receptive field (RF) properties of V1 neurons or if some aspects are sufficient. Here, we explore this question by building several variants of a CNN model with a front-end modeling the primate V1 using a classical neuroscientific model, a Gabor Filter Bank (GFB) followed by simple- and complex- cell nonlinearities. Each model variant had varying levels of biological detail according to how the RF properties were sampled. The model variant sampling these parameters according to empirical biological distributions was considerably more robust to image corruptions than the variant sampling the parameters uniformly and independently (relative difference of 8.72%). However, a uniform variant capturing correlations between some GFB parameters obtained the same performance as the biological sampling variant. Our results show that it is not sufficient to approximate V1 with only the right class of function and parameter range, as it is also required to include the observed correlations between RF properties. However, it is not necessary to fully replicate the empirical distributions of V1 RF properties to obtain the desired improvement in robustness.<\/jats:p>","DOI":"10.3233\/faia240546","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:48:23Z","timestamp":1729169303000},"source":"Crossref","is-referenced-by-count":0,"title":["Contribution of V1 Receptive Field Properties to Corruption Robustness in CNNs"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8960-5329","authenticated-orcid":false,"given":"Ruxandra","family":"Barbulescu","sequence":"first","affiliation":[{"name":"INESC-ID, Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8973-0549","authenticated-orcid":false,"given":"Tiago","family":"Marques","sequence":"additional","affiliation":[{"name":"Breast Unit, Champalimaud Clinical Center, Champalimaud Foundation, Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8638-5594","authenticated-orcid":false,"given":"Arlindo L.","family":"Oliveira","sequence":"additional","affiliation":[{"name":"INESC-ID, Lisboa, Portugal"},{"name":"Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:48:23Z","timestamp":1729169303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240546","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"type":"print","value":"0922-6389"},{"type":"electronic","value":"1879-8314"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}