{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T13:05:53Z","timestamp":1793711153520,"version":"4.6.1"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729799","type":"print"},{"value":"9783031729805","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72980-5_26","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T05:15:43Z","timestamp":1730092543000},"page":"444-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Discover-then-Name: Task-Agnostic Concept Bottlenecks via\u00a0Automated Concept Discovery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8896-7619","authenticated-orcid":false,"given":"Sukrut","family":"Rao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8811-8771","authenticated-orcid":false,"given":"Sweta","family":"Mahajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-3769","authenticated-orcid":false,"given":"Moritz","family":"B\u00f6hle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-5237","authenticated-orcid":false,"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"issue":"9","key":"26_CR1","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1038\/s42256-023-00711-8","volume":"5","author":"R Achtibat","year":"2023","unstructured":"Achtibat, R., et al.: From attribution maps to human-understandable explanations through concept relevance propagation. Nat. Mach. Intell. 5(9), 1006\u20131019 (2023)","journal-title":"Nat. Mach. Intell."},{"key":"26_CR2","unstructured":"Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: NeurIPS, vol.\u00a031 (2018)"},{"key":"26_CR3","unstructured":"Adebayo, J., Muelly, M., Abelson, H., Kim, B.: Post hoc explanations may be ineffective for detecting unknown spurious correlation. In: ICLR (2021)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Alukaev, D., et al.: Cross-modal conceptualization in bottleneck models. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.318"},{"issue":"7","key":"26_CR5","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)","journal-title":"PLoS ONE"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: CVPR, pp. 6541\u20136549 (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"26_CR7","unstructured":"Bhalla, U., Oesterling, A., Srinivas, S., Calmon, F.P., Lakkaraju, H.: Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE). arXiv preprint arXiv:2402.10376 (2024)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"B\u00f6hle, M., Fritz, M., Schiele, B.: B-cos networks: alignment is all we need for interpretability. In: CVPR, pp. 10329\u201310338 (2022)","DOI":"10.1109\/CVPR52688.2022.01008"},{"key":"26_CR9","unstructured":"Bricken, T., et al.: Towards monosemanticity: decomposing language models with dictionary learning. Transformer Circ. Thread (2023)"},{"key":"26_CR10","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS, vol.\u00a033, pp. 1877\u20131901 (2020)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Chauhan, K., Tiwari, R., Freyberg, J., Shenoy, P., Dvijotham, D.: Interactive concept bottleneck models. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i5.25736"},{"key":"26_CR12","unstructured":"Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: NeurIPS, vol.\u00a032 (2019)"},{"key":"26_CR13","unstructured":"Chen, H., Yang, J., Vondrick, C., Mao, C.: Interpreting and controlling vision foundation models via text explanations. arXiv preprint arXiv:2310.10591 (2023)"},{"key":"26_CR14","unstructured":"Cunningham, H., Ewart, A., Riggs, L., Huben, R., Sharkey, L.: Sparse autoencoders find highly interpretable features in language models. arXiv preprint arXiv:2309.08600 (2023)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Dani, M., Rio-Torto, I., Alaniz, S., Akata, Z.: DeViL: decoding vision features into language. In: GCPR (2023)","DOI":"10.1007\/978-3-031-54605-1_24"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"26_CR18","unstructured":"Elhage, N., et\u00a0al.: Toy models of superposition. arXiv preprint arXiv:2209.10652 (2022)"},{"key":"26_CR19","unstructured":"Fel, T., et al.: A holistic approach to unifying automatic concept extraction and concept importance estimation. In: NeurIPS, vol.\u00a036 (2023)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Fel, T., et al.: CRAFT: concept recursive activation factorization for explainability. In: CVPR, pp. 2711\u20132721 (2023)","DOI":"10.1109\/CVPR52729.2023.00266"},{"key":"26_CR21","unstructured":"Ghorbani, A., Wexler, J., Zou, J.Y., Kim, B.: Towards automatic concept-based explanations. In: NeurIPS, vol.\u00a032 (2019)"},{"key":"26_CR22","unstructured":"Graziani, M., Nguyen, A.P., O\u2019Mahony, L., M\u00fcller, H., Andrearczyk, V.: Concept discovery and dataset exploration with singular value decomposition. In: ICLRW (2023)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46493-0_1","volume-title":"Computer Vision \u2013 ECCV 2016","author":"LA Hendricks","year":"2016","unstructured":"Hendricks, L.A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., Darrell, T.: Generating visual explanations. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 3\u201319. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_1"},{"key":"26_CR25","unstructured":"Hernandez, E., Schwettmann, S., Bau, D., Bagashvili, T., Torralba, A., Andreas, J.: Natural language descriptions of deep visual features. In: ICLR (2022)"},{"key":"26_CR26","unstructured":"Jeyakumar, J.V., et al.: Automatic concept extraction for concept bottleneck-based video classification. arXiv preprint arXiv:2206.10129 (2022)"},{"key":"26_CR27","unstructured":"Kazmierczak, R., Berthier, E., Frehse, G., Franchi, G.: CLIP-QDA: an explainable concept bottleneck model. arXiv preprint arXiv:2312.00110 (2023)"},{"key":"26_CR28","unstructured":"Kim, B., et\u00a0al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: ICML, pp. 2668\u20132677 (2018)"},{"key":"26_CR29","unstructured":"Kim, E., Jung, D., Park, S., Kim, S., Yoon, S.: Probabilistic Concept Bottleneck Models. In: ICML (2023)"},{"key":"26_CR30","unstructured":"Koh, P.W., et al.: Concept bottleneck models. In: ICML, pp. 5338\u20135348 (2020)"},{"key":"26_CR31","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images. Technical report, Computer Science Department, University of Toronto (2009)"},{"key":"26_CR32","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. NeurIPS 30 (2017)"},{"key":"26_CR33","unstructured":"Margeloiu, A., Ashman, M., Bhatt, U., Chen, Y., Jamnik, M., Weller, A.: Do concept bottleneck models learn as intended? In: ICLRW (2021)"},{"key":"26_CR34","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: ICLR (2023)"},{"key":"26_CR35","unstructured":"Moayeri, M., Rezaei, K., Sanjabi, M., Feizi, S.: Text-to-concept (and back) via cross-model alignment. In: ICML, pp. 25037\u201325060. PMLR (2023)"},{"key":"26_CR36","unstructured":"Oikarinen, T., Das, S., Nguyen, L.M., Weng, T.W.: Label-free concept bottleneck models. In: ICLR (2023)"},{"key":"26_CR37","unstructured":"Oikarinen, T., Weng, T.W.: CLIP-dissect: automatic description of neuron representations in deep vision networks. In: ICLR (2023)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"O\u2019Mahony, L., Andrearczyk, V., M\u00fcller, H., Graziani, M.: Disentangling neuron representations with concept vectors. In: CVPRW, pp. 3769\u20133774 (2023)","DOI":"10.1109\/CVPRW59228.2023.00390"},{"key":"26_CR39","unstructured":"Panousis, K.P., Chatzis, S.: DISCOVER: making vision networks interpretable via competition and dissection. In: NeurIPS (2023)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Panousis, K.P., Ienco, D., Marcos, D.: Hierarchical concept discovery models: a concept pyramid scheme. arXiv preprint arXiv:2310.02116 (2023)","DOI":"10.1109\/ICCVW60793.2023.00292"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Panousis, K.P., Ienco, D., Marcos, D.: Sparse linear concept discovery models. In: ICCVW, pp. 2767\u20132771 (2023)","DOI":"10.1109\/ICCVW60793.2023.00292"},{"issue":"1\u20132","key":"26_CR42","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s11263-013-0695-z","volume":"108","author":"G Patterson","year":"2014","unstructured":"Patterson, G., Xu, C., Su, H., Hays, J.: The SUN attribute database: beyond categories for deeper scene understanding. IJCV 108(1\u20132), 59\u201381 (2014)","journal-title":"IJCV"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Petryk, S., Dunlap, L., Nasseri, K., Gonzalez, J., Darrell, T., Rohrbach, A.: On guiding visual attention with language specification. In: CVPR, pp. 18092\u201318102 (2022)","DOI":"10.1109\/CVPR52688.2022.01756"},{"key":"26_CR44","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Rao, S., B\u00f6hle, M., Parchami-Araghi, A., Schiele, B.: Studying how to efficiently and effectively guide models with explanations. In: ICCV, pp. 1922\u20131933 (2023)","DOI":"10.1109\/ICCV51070.2023.00184"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Rao, S., B\u00f6hle, M., Schiele, B.: Towards better understanding attribution methods. In: CVPR, pp. 10213\u201310222 (2022)","DOI":"10.1109\/CVPR52688.2022.00998"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cWhy should I trust you?\u201d explaining the predictions of any classifier. In: KDD, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Ross, A.S., Hughes, M.C., Doshi-Velez, F.: Right for the right reasons: training differentiable models by constraining their explanations. In: IJCAI, pp. 2662\u20132670 (2017)","DOI":"10.24963\/ijcai.2017\/371"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Roth, K., Kim, J.M., Koepke, A.S., Vinyals, O., Schmid, C., Akata, Z.: Waffling around for performance: visual classification with random words and broad concepts. In: ICCV, pp. 15746\u201315757 (2023)","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"26_CR50","unstructured":"Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks. In: ICLR (2020)"},{"key":"26_CR51","doi-asserted-by":"publisher","first-page":"41758","DOI":"10.1109\/ACCESS.2022.3167702","volume":"10","author":"Y Sawada","year":"2022","unstructured":"Sawada, Y., Nakamura, K.: Concept bottleneck model with additional unsupervised concepts. IEEE Access 10, 41758\u201341765 (2022)","journal-title":"IEEE Access"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"26_CR53","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"26_CR54","unstructured":"Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: ICML, pp. 3145\u20133153. PMLR (2017)"},{"key":"26_CR55","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML, pp. 3319\u20133328. PMLR (2017)"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Tewel, Y., Shalev, Y., Schwartz, I., Wolf, L.: ZeroCap: zero-shot image-to-text generation for visual-semantic arithmetic. In: CVPR, pp. 17918\u201317928 (2022)","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"26_CR57","unstructured":"Xu, X., Qin, Y., Mi, L., Wang, H., Li, X.: Energy-based concept bottleneck models: unifying prediction, concept intervention, and conditional interpretations. In: ICLR (2024)"},{"key":"26_CR58","doi-asserted-by":"crossref","unstructured":"Yang, Y., Panagopoulou, A., Zhou, S., Jin, D., Callison-Burch, C., Yatskar, M.: Language in a bottle: language model guided concept bottlenecks for interpretable image classification. In: CVPR, pp. 19187\u201319197 (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"26_CR59","unstructured":"Yuksekgonul, M., Wang, M., Zou, J.: Post-hoc concept bottleneck models. In: ICLR (2023)"},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, R., Madumal, P., Miller, T., Ehinger, K.A., Rubinstein, B.I.: Invertible concept-based explanations for CNN models with non-negative concept activation vectors. In: AAAI, pp. 11682\u201311690 (2021)","DOI":"10.1609\/aaai.v35i13.17389"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Zhao, C., Qian, W., Shi, Y., Huai, M., Liu, N.: Automated natural language explanation of deep visual neurons with large models. arXiv preprint arXiv:2310.10708 (2023)","DOI":"10.1609\/aaai.v38i21.30537"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2017)","DOI":"10.1167\/17.10.296"},{"key":"26_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01237-3_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Sun, Y., Bau, D., Torralba, A.: Interpretable basis decomposition for visual explanation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_8"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72980-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T05:25:10Z","timestamp":1730093110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72980-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031729799","9783031729805"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72980-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}