{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T14:41:51Z","timestamp":1765982511667,"version":"3.48.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Interact. Intell. Syst."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>Improving the modeling of human representations of everyday semantic categories, such as animals or food, can lead to better alignment between AI systems and humans. Humans are thought to represent such categories using dimensions that capture relevant variance, in this way defining the relationship between category members. In AI systems, the representational space for a category is defined by the distances between its members. Importantly, in this context, the same features are used for distance computations across all categories. In two experiments, we show that pruning a model\u2019s feature space to better align with human representations of a category selects for different model features and different subspaces for different categories. In addition, we provide a proof of concept demonstrating the relevance of these findings for evaluating the quality of images generated by AI systems.<\/jats:p>","DOI":"10.1145\/3768340","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T09:18:49Z","timestamp":1758532729000},"page":"1-25","update-policy":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Modeling Human Concepts with Subspaces in Deep Vision\u00a0Models"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/orcid.org\/0009-0004-3854-0616","authenticated-orcid":false,"given":"Anna","family":"Bavaresco","sequence":"first","affiliation":[{"name":"CIMeC, Center for Mind\/Brain Sciences, University of Trento, Trento, Italy and Institute for Logic, Language and Computation, University of Amsterdam, Amsterdam, Holland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/orcid.org\/0009-0000-8758-9257","authenticated-orcid":false,"given":"Nhut","family":"Truong","sequence":"additional","affiliation":[{"name":"CIMeC, Center for Mind\/Brain Sciences, University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/orcid.org\/0000-0002-8530-5051","authenticated-orcid":false,"given":"Uri","family":"Hasson","sequence":"additional","affiliation":[{"name":"CIMeC, Center for Mind\/Brain Sciences, University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.945094"},{"key":"e_1_3_2_3_2","volume-title":"Proceedings of the NeurIPS 2020 Workshop on Shared Visual Representations in Human and Machine Intelligence (SVRHM)","author":"Attarian Ioanna Maria","year":"2020","unstructured":"Ioanna Maria Attarian, Brett D. Roads, and Michael Curtis Mozer. 2020. Transforming neural network visual representations to predict human judgments of similarity. In Proceedings of the NeurIPS 2020 Workshop on Shared Visual Representations in Human and Machine Intelligence (SVRHM)."},{"key":"e_1_3_2_4_2","unstructured":"Wanqian Bao and Uri Hasson. 2024. Identifying and interpreting non-aligned human conceptual representations using language modeling. In Proceedings of the ICLR 2024 Workshop on Representational Alignment. Retrieved from https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/openreview.net\/forum?id=vh56Q8wbGK"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.74"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.01.009"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_8_2","first-page":"3","article-title":"On the \u201cprobable error\u201d of a coefficient of correlation deduced from a small sample","volume":"1","author":"Fisher Ronald A.","year":"1921","unstructured":"Ronald A. Fisher. 1921. On the \u201cprobable error\u201d of a coefficient of correlation deduced from a small sample. Metron 1 (1921), 3\u201332.","journal-title":"Metron"},{"key":"e_1_3_2_9_2","article-title":"Enhancing interpretability using human similarity judgements to prune word embeddings","author":"Flechas Manrique Natalia","year":"2023","unstructured":"Natalia Flechas Manrique, Wanqian Bao, Aurelie Herbelot, and Uri Hasson. 2023. Enhancing interpretability using human similarity judgements to prune word embeddings. In Proceedings of BlackboxNLP at EMNLP 2023.","journal-title":"Proceedings of BlackboxNLP at EMNLP 2023"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-23618-6"},{"key":"e_1_3_2_11_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Geirhos Robert","year":"2018","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, and Wieland Brendel. 2018. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.32962"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11229-023-04461-3"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944968"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0223792"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-020-00951-3"},{"key":"e_1_3_2_17_2","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In Advances in Neural Information Processing Systems. I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30, Curran Associates, Inc. Retrieved from https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a1d694707eb0fefe65871369074926d-Paper.pdf"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2011.13"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119294"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.04.079"},{"key":"e_1_3_2_21_2","first-page":"36652","article-title":"Pick-a-Pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-Pic: An open dataset of user preferences for text-to-image generation. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36, 36652\u201336663.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3728458"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00245"},{"key":"e_1_3_2_24_2","first-page":"249","article-title":"Representational similarity analysis-connecting the branches of systems neuroscience","volume":"2","author":"Kriegeskorte Nikolaus","year":"2008","unstructured":"Nikolaus Kriegeskorte, Marieke Mur, and Peter A. Bandettini. 2008. Representational similarity analysis-connecting the branches of systems neuroscience. Frontiers in Systems Neuroscience 2 (2008), 249.","journal-title":"Frontiers in Systems Neuroscience"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1080\/09515080050002726"},{"key":"e_1_3_2_26_2","volume-title":"Proceedings of the Annual Meeting of the Cognitive Science Society","volume":"37","author":"Lake Brenden M.","year":"2015","unstructured":"Brenden M. Lake, Wojciech Zaremba, Rob Fergus, and Todd M. Gureckis. 2015. Deep neural networks predict category typicality ratings for images. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 37."},{"key":"e_1_3_2_27_2","first-page":"67","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Mallya Arun","year":"2018","unstructured":"Arun Mallya, Dillon Davis, and Svetlana Lazebnik. 2018. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In Proceedings of the European Conference on Computer Vision (ECCV), 67\u201382."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2995909"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.12670"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00971"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1971.10482356"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.13030"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00355"},{"key":"e_1_3_2_36_2","first-page":"27","volume-title":"Cognition and Categorization","author":"Rosch Eleanor","year":"1978","unstructured":"Eleanor Rosch. 1978. Principles of categorization. In Cognition and Categorization. Eleanor Rosch and Barbara B. Lloyd (Eds.), Lawrence Erlbaum, Hillsdale, NJ, 27\u201348."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_39_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations (ICLR 2015) San Diego CA USA May 7\u20139 2015 Conference Track Proceedings."},{"key":"e_1_3_2_40_2","unstructured":"D. S. Soper. 2023. Significance of the Difference between Two Correlations Calculator [Software]. Retrieved from https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/www.danielsoper.com\/statcalc"},{"key":"e_1_3_2_41_2","unstructured":"Ilia Sucholutsky Lukas Muttenthaler Adrian Weller Andi Peng Andreea Bobu Been Kim Bradley C. Love Erin Grant Jascha Achterberg Joshua B. Tenenbaum et al. 2023. Getting aligned on representational alignment. arXiv:2310.13018. Retrieved from https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/arxiv.org\/abs\/2310.13018"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.08.049"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42113-025-00235-x"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030383"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["ACM Transactions on Interactive Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3768340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T14:37:23Z","timestamp":1765982243000},"score":1,"resource":{"primary":{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3768340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3768340"],"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1145\/3768340","relation":{},"ISSN":["2160-6455","2160-6463"],"issn-type":[{"type":"print","value":"2160-6455"},{"type":"electronic","value":"2160-6463"}],"subject":[],"published":{"date-parts":[[2025,12,10]]},"assertion":[{"value":"2024-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}