{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:46:34Z","timestamp":1757623594709,"version":"3.44.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Korea Internet & Security Agenc","award":["No.RS-2023-00231200"],"award-info":[{"award-number":["No.RS-2023-00231200"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s11263-025-02474-8","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T17:03:08Z","timestamp":1748451788000},"page":"6201-6220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification"],"prefix":"10.1007","volume":"133","author":[{"given":"Youngjae","family":"Song","sequence":"first","affiliation":[]},{"given":"Sung Kuk","family":"Shyn","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1097-8112","authenticated-orcid":false,"given":"Kwang-su","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"issue":"227","key":"2474_CR1","first-page":"357","volume":"39","author":"J Berkson","year":"1944","unstructured":"Berkson, J. (1944). Application of the logistic function to bio-assay. Journal of the American statistical association, 39(227), 357\u2013365.","journal-title":"Journal of the American statistical association"},{"issue":"4","key":"2474_CR2","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","volume":"13","author":"MA Hearst","year":"1998","unstructured":"Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J., & Scholkopf, B. (1998). Support vector machines. IEEE Intelligent Systems and their applications, 13(4), 18\u201328.","journal-title":"IEEE Intelligent Systems and their applications"},{"key":"2474_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"2474_CR4","doi-asserted-by":"publisher","first-page":"6679","DOI":"10.1609\/aaai.v35i8.16826","volume":"35","author":"S\u00d6 Arik","year":"2021","unstructured":"Arik, S. \u00d6., & Pfister, T. (2021). Tabnet: Attentive interpretable tabular learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 35, 6679\u20136687.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2474_CR5","unstructured":"Borisov, V., Leemann, T., Se\u00dfler, K., Haug, J., Pawelczyk, M., & Kasneci, G. (2021). Deep neural networks and tabular data: A survey. arXiv preprint arXiv:2110.01889."},{"key":"2474_CR6","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020). Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"2474_CR7","doi-asserted-by":"crossref","unstructured":"Nitzan, Y., Gal, R., Brenner, O., & Cohen-Or, D. (2022). Large: Latent-based regression through gan semantics. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19239\u201319249.","DOI":"10.1109\/CVPR52688.2022.01864"},{"key":"2474_CR8","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., & Shechtman, E. (2021). Stylespace analysis: Disentangled controls for stylegan image generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12863\u201312872.","DOI":"10.1109\/CVPR46437.2021.01267"},{"issue":"4","key":"2474_CR9","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1287\/mnsc.6.4.366","volume":"6","author":"LV Kantorovich","year":"1960","unstructured":"Kantorovich, L. V. (1960). Mathematical methods of organizing and planning production. Management science, 6(4), 366\u2013422.","journal-title":"Management science"},{"key":"2474_CR10","unstructured":"Molnar, C. (2018). A guide for making black box models explainable. https:\/\/christophm.github.io\/interpretable-ml-book."},{"key":"2474_CR11","doi-asserted-by":"crossref","unstructured":"Kulesza, T., Burnett, M., Wong, W.-K., & Stumpf, S. (2015). Principles of explanatory debugging to personalize interactive machine learning. In Proceedings of the 20th International Conference on Intelligent User Interfaces, pp. 126\u2013137.","DOI":"10.1145\/2678025.2701399"},{"key":"2474_CR12","doi-asserted-by":"crossref","unstructured":"Kulesza, T., Stumpf, S., Burnett, M., Wong, W.-K., Riche, Y., Moore, T., Oberst, I., Shinsel, A., & McIntosh, K. (2010). Explanatory debugging: Supporting end-user debugging of machine-learned programs. In 2010 IEEE Symposium on Visual Languages and Human-Centric Computing, pp. 41\u201348.. IEEE","DOI":"10.1109\/VLHCC.2010.15"},{"key":"2474_CR13","doi-asserted-by":"crossref","unstructured":"Zylberajch, H., Lertvittayakumjorn, P., & Toni, F. (2021). Hildif: Interactive debugging of nli models using influence functions. In Proceedings of the First Workshop on Interactive Learning for Natural Language Processing, pp. 1\u20136.","DOI":"10.18653\/v1\/2021.internlp-1.1"},{"key":"2474_CR14","doi-asserted-by":"crossref","unstructured":"Balayn, A., Rikalo, N., Lofi, C., Yang, J., & Bozzon, A. (2022). How can explainability methods be used to support bug identification in computer vision models? In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pp. 1\u201316.","DOI":"10.1145\/3491102.3517474"},{"issue":"3","key":"2474_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447648","volume":"40","author":"R Abdal","year":"2021","unstructured":"Abdal, R., Zhu, P., Mitra, N. J., & Wonka, P. (2021). Styleflow: Attribute-conditioned exploration of stylegan-generated images using conditional continuous normalizing flows. ACM Transactions on Graphics (ToG), 40(3), 1\u201321.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"2474_CR16","first-page":"9841","volume":"33","author":"E H\u00e4rk\u00f6nen","year":"2020","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., & Paris, S. (2020). Ganspace: Discovering interpretable gan controls. Advances in Neural Information Processing Systems, 33, 9841\u20139850.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2474_CR17","unstructured":"Shen, Y., Yang, C., Tang, X., & Zhou, B. (2020). Interfacegan: Interpreting the disentangled face representation learned by gans. IEEE transactions on pattern analysis and machine intelligence."},{"key":"2474_CR18","unstructured":"Dumoulin, V., Belghazi, I., Poole, B., Mastropietro, O., Lamb, A., Arjovsky, M., & Courville, A. (2016). Adversarially learned inference. arXiv preprint arXiv:1606.00704."},{"issue":"4","key":"2474_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., & Cohen-Or, D. (2021). Designing an encoder for stylegan image manipulation. ACM Transactions on Graphics (TOG), 40(4), 1\u201314.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2474_CR20","doi-asserted-by":"crossref","unstructured":"Richardson, E., Alaluf, Y., Patashnik, O., Nitzan, Y., Azar, Y., Shapiro, S., & Cohen-Or, D. (2021). Encoding in style: a stylegan encoder for image-to-image translation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2287\u20132296.","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"2474_CR21","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Tov, O., Mokady, R., Gal, R., & Bermano, A. (2022). Hyperstyle: Stylegan inversion with hypernetworks for real image editing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18511\u201318521.","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"2474_CR22","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Patashnik, O., & Cohen-Or, D. (2021). Restyle: A residual-based stylegan encoder via iterative refinement. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6711\u20136720.","DOI":"10.1109\/ICCV48922.2021.00664"},{"issue":"1","key":"2474_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544777","volume":"42","author":"D Roich","year":"2022","unstructured":"Roich, D., Mokady, R., Bermano, A. H., & Cohen-Or, D. (2022). Pivotal tuning for latent-based editing of real images. ACM Transactions on Graphics (TOG), 42(1), 1\u201313.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2474_CR24","doi-asserted-by":"crossref","unstructured":"Xu, Y., Shen, Y., Zhu, J., Yang, C., & Zhou, B. (2021). Generative hierarchical features from synthesizing images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4432\u20134442.","DOI":"10.1109\/CVPR46437.2021.00441"},{"key":"2474_CR25","unstructured":"Donahue, J., Kr\u00e4henb\u00fchl, P., & Darrell, T. (2016). Adversarial feature learning. arXiv preprint arXiv:1605.09782."},{"key":"2474_CR26","unstructured":"Donahue, J., & Simonyan, K. (2019) Large scale adversarial representation learning. Advances in neural information processing systems, 32."},{"key":"2474_CR27","unstructured":"Dorogush, A. V., Ershov, V., & Gulin, A. (2018). Catboost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363."},{"key":"2474_CR28","unstructured":"Koh, P. W., Nguyen, T., Tang, Y. S., Mussmann, S., Pierson, E., Kim, B., & Liang, P. (2020). Concept bottleneck models. In International Conference on Machine Learning, pp. 5338\u20135348. PMLR"},{"key":"2474_CR29","unstructured":"Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & others. (2018). Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In International Conference on Machine Learning, pp. 2668\u20132677 PMLR"},{"key":"2474_CR30","doi-asserted-by":"publisher","first-page":"2594","DOI":"10.1609\/aaai.v34i03.5643","volume":"34","author":"A Akula","year":"2020","unstructured":"Akula, A., Wang, S., & Zhu, S.-C. (2020). Cocox: Generating conceptual and counterfactual explanations via fault-lines. In Proceedings of the AAAI Conference on Artificial Intelligence, 34, 2594\u20132601.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2474_CR31","unstructured":"Alvarez\u00a0Melis, D., & Jaakkola, T. (2018). Towards robust interpretability with self-explaining neural networks. Advances in neural information processing systems, 31."},{"key":"2474_CR32","first-page":"20554","volume":"33","author":"C-K Yeh","year":"2020","unstructured":"Yeh, C.-K., Kim, B., Arik, S., Li, C.-L., Pfister, T., & Ravikumar, P. (2020). On completeness-aware concept-based explanations in deep neural networks. Advances in Neural Information Processing Systems, 33, 20554\u201320565.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2474_CR33","doi-asserted-by":"crossref","unstructured":"Sarkar, A., Vijaykeerthy, D., Sarkar, A., & Balasubramanian, V. N. (2022). A framework for learning ante-hoc explainable models via concepts. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10286\u201310295.","DOI":"10.1109\/CVPR52688.2022.01004"},{"key":"2474_CR34","unstructured":"Ghorbani, A., Wexler, J., Zou, J. Y., & Kim, B. (2019). Towards automatic concept-based explanations. Advances in Neural Information Processing Systems, 32."},{"key":"2474_CR35","unstructured":"Ghandeharioun, A., Kim, B., Li, C.-L., Jou, B., Eoff, B., Picard, R. W. (2021). Dissect: Disentangled simultaneous explanations via concept traversals. arXiv preprint arXiv:2105.15164."},{"key":"2474_CR36","unstructured":"Singla, S., Pollack, B., Chen, J., & Batmanghelich, K. (2019). Explanation by progressive exaggeration. arXiv preprint arXiv:1911.00483."},{"key":"2474_CR37","doi-asserted-by":"crossref","unstructured":"Lang, O., Gandelsman, Y., Yarom, M., Wald, Y., Elidan, G., Hassidim, A., Freeman, W.T., Isola, P., Globerson, A., Irani, M., & others. (2021) Explaining in style: Training a gan to explain a classifier in stylespace. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 693\u2013702","DOI":"10.1109\/ICCV48922.2021.00073"},{"key":"2474_CR38","unstructured":"Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems 30."},{"issue":"1","key":"2474_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2514\/atcq.9.1.1","volume":"9","author":"KD Bilimoria","year":"2001","unstructured":"Bilimoria, K. D., Sridhar, B., Grabbe, S. R., Chatterji, G. B., & Sheth, K. S. (2001). Facet: Future atm concepts evaluation tool. Air Traffic Control Quarterly, 9(1), 1\u201320.","journal-title":"Air Traffic Control Quarterly"},{"issue":"2","key":"2474_CR40","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1037\/h0043158","volume":"63","author":"GA Miller","year":"1956","unstructured":"Miller, G. A. (1956). The magical number seven, plus or minus two: Some limits on our capacity for processing information. Psychological review, 63(2), 81.","journal-title":"Psychological review"},{"key":"2474_CR41","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2474_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"2474_CR43","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., & others. (2019) Searching for mobilenetv3. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"2474_CR44","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"2474_CR45","unstructured":"Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, pp. 6105\u20136114. PMLR"},{"key":"2474_CR46","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"issue":"5786","key":"2474_CR47","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504\u2013507.","journal-title":"science"},{"key":"2474_CR48","doi-asserted-by":"crossref","unstructured":"Pidhorskyi, S., Adjeroh, D. A., & Doretto, G. (2020). Adversarial latent autoencoders. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14104\u201314113.","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"2474_CR49","doi-asserted-by":"crossref","unstructured":"Li, A. C., Prabhudesai, M., Duggal, S., Brown, E., & Pathak, D. (2023). Your diffusion model is secretly a zero-shot classifier. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2206\u20132217","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"2474_CR50","first-page":"58921","volume":"36","author":"K Clark","year":"2023","unstructured":"Clark, K., & Jaini, P. (2023). Text-to-image diffusion models are zero shot classifiers. Advances in Neural Information Processing Systems, 36, 58921\u201358937.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2474_CR51","doi-asserted-by":"crossref","unstructured":"Li, H., Shen, C., Torr, P., Tresp, V., Gu, J. (2024). Self-discovering interpretable diffusion latent directions for responsible text-to-image generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12006\u201312016.","DOI":"10.1109\/CVPR52733.2024.01141"},{"key":"2474_CR52","doi-asserted-by":"crossref","unstructured":"Guo, J., Xu, X., Pu, Y., Ni, Z., Wang, C., Vasu, M., Song, S., Huang, G., & Shi, H. (2024). Smooth diffusion: Crafting smooth latent spaces in diffusion models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7548\u20137558.","DOI":"10.1109\/CVPR52733.2024.00721"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02474-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02474-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02474-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T08:08:07Z","timestamp":1757405287000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02474-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":52,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["2474"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02474-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2025,5,28]]},"assertion":[{"value":"17 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}