{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:47:26Z","timestamp":1771458446965,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3316718","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T17:59:26Z","timestamp":1695146366000},"page":"14575-14589","source":"Crossref","is-referenced-by-count":5,"title":["Fine-Grained Species Recognition With Privileged Pooling: Better Sample Efficiency Through Supervised Attention"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7446-5690","authenticated-orcid":false,"given":"Andr\u00e9s C.","family":"Rodr\u00edguez","sequence":"first","affiliation":[{"name":"EcoVision Lab - Photogrammetry and Remote Sensing, ETH Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0142-1731","authenticated-orcid":false,"given":"Stefano","family":"D\u2019Aronco","sequence":"additional","affiliation":[{"name":"EcoVision Lab - Photogrammetry and Remote Sensing, ETH Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3172-9246","authenticated-orcid":false,"given":"Konrad","family":"Schindler","sequence":"additional","affiliation":[{"name":"EcoVision Lab - Photogrammetry and Remote Sensing, ETH Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0290-6901","authenticated-orcid":false,"given":"Jan Dirk","family":"Wegner","sequence":"additional","affiliation":[{"name":"EcoVision Lab - Photogrammetry and Remote Sensing, ETH Zurich, Zürich, Switzerland"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1894","article-title":"On the theory of learnining with privileged information","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pechyony"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.635"},{"key":"ref3","article-title":"SPIGAN: Privileged adversarial learning from simulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00926"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.166"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"ref11","first-page":"2940","article-title":"Cognitive psychology for deep neural networks: A shape bias case study","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ritter"},{"key":"ref12","article-title":"See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification","author":"Hu","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"ref15","first-page":"34","article-title":"Attentional pooling for action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Girdhar"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref17","article-title":"Caltech-UCSD birds 200","author":"Welinder","year":"2010"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.107"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.96"},{"key":"ref20","article-title":"Face verification from depth using privileged information","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Borghi"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref23","article-title":"Unifying distillation and privileged information","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lopez-Paz"},{"key":"ref24","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref25","article-title":"Learning what and where to transfer","author":"Jang","year":"2019"},{"key":"ref26","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.12.007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref29","first-page":"525","article-title":"Multi-task learning as multi-objective optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sener"},{"key":"ref30","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall"},{"key":"ref31","article-title":"Adapting auxiliary losses using gradient similarity","author":"Du","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref33","article-title":"Measuring compositionality in representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Andreas"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00647"},{"key":"ref35","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.228"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"ref49","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref51","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization","author":"Khosla"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref55","article-title":"ImageNet-21k pretraining for the masses","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ridnik"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref57","article-title":"How to train your ViT? data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10255365.pdf?arnumber=10255365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T03:03:15Z","timestamp":1709348595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10255365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":57,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3316718","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}