{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:32:02Z","timestamp":1758123122536,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":55,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819608843"},{"type":"electronic","value":"9789819608850"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0885-0_16","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T08:02:04Z","timestamp":1733472124000},"page":"277-295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Image Clustering with\u00a0Artifacts Attenuation via\u00a0Inference-Time Attention Engineering"],"prefix":"10.1007","author":[{"given":"Kazumoto","family":"Nakamura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"Nozawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Chieh","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kengo","family":"Nakata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youyang","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"16_CR1","unstructured":"Adaloglou, N., Michels, F., Kalisch, H., Kollmann, M.: Exploring the limits of deep image clustering using pretrained models. arXiv preprint arXiv:2303.17896 (2023)"},{"key":"16_CR2","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., Amodei, D.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems (2020)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Proceedings of the European conference on computer vision (ECCV). pp. 132\u2013149 (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 9630\u20139640. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chang, J., Wang, L., Meng, G., Xiang, S., Pan, C.: Deep adaptive image clustering. In: Proceedings of the IEEE international conference on computer vision. pp. 5879\u20135887 (2017)","DOI":"10.1109\/ICCV.2017.626"},{"key":"16_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning. pp. 1597\u20131607. PMLR (2020)"},{"key":"16_CR7","first-page":"22243","volume":"33","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. Adv. Neural. Inf. Process. Syst. 33, 22243\u201322255 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: Zero-shot object-level image customization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6593\u20136602 (June 2024)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., Hu, Q., Li, K., Zhong, C., Wang, G.: Accumulated trivial attention matters in vision transformers on small datasets. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 3973\u20133981. IEEE (2023)","DOI":"10.1109\/WACV56688.2023.00397"},{"key":"16_CR10","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 9620\u20139629. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"16_CR13","unstructured":"Chu, T., Tong, S., Ding, T., Dai, X., Haeffele, B.D., Vidal, R., Ma, Y.: Image clustering via the principle of rate reduction in the age of pretrained models. arXiv preprint arXiv:2306.05272 (2023)"},{"key":"16_CR14","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics. pp. 215\u2013223. JMLR Workshop and Conference Proceedings (2011)"},{"key":"16_CR15","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"16_CR16","unstructured":"Dilokthanakul, N., Mediano, P.A., Garnelo, M., Lee, M.C., Salimbeni, H., Arulkumaran, K., Shanahan, M.: Deep unsupervised clustering with gaussian mixture variational autoencoders. arXiv preprint arXiv:1611.02648 (2016)"},{"key":"16_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"16_CR18","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9726\u20139735. IEEE Computer Society (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"5786","key":"16_CR20","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.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 9865\u20139874 (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"16_CR22","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International conference on machine learning. pp. 4904\u20134916. PMLR (2021)"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, Y., Tan, H., Tang, B., Zhou, H.: Variational deep embedding: An unsupervised and generative approach to clustering. arXiv preprint arXiv:1611.05148 (2016)","DOI":"10.24963\/ijcai.2017\/273"},{"key":"16_CR24","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: Proceedings of the 36th International Conference on Neural Information Processing Systems (2024)"},{"key":"16_CR25","unstructured":"Krizhevsky, A., Hinton., G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)"},{"key":"16_CR26","unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)"},{"key":"16_CR27","unstructured":"Lee, S.H., Lee, S., Song, B.C.: Vision transformer for small-size datasets. arXiv preprint arXiv:2112.13492 (2021)"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: European Conference on Computer Vision. pp. 280\u2013296. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"16_CR29","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision - ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision - ECCV 2014, pp. 740\u2013755. Springer International Publishing, Cham (2014)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"16_CR31","unstructured":"Lowe, S., Haurum, J., Oore, S., Moeslund, T., Taylor, G.: Zero-shot clustering of embeddings with pretrained and self-supervised learnt encoders. In: Workshop on robustness of zero\/few-shot learning in foundation models (NeurIPS 2023) (2023)"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Mukherjee, S., Asnani, H., Lin, E., Kannan, S.: Clustergan: Latent space clustering in generative adversarial networks. In: Proceedings of the AAAI conference on artificial intelligence. pp. 4610\u20134617 (2019)","DOI":"10.1609\/aaai.v33i01.33014610"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Nakata, K., Ng, Y., Miyashita, D., Maki, A., Lin, Y.C., Deguchi, J.: Revisiting a knn-based image classification system with high-capacity storage. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19836-6_26"},{"key":"16_CR34","unstructured":"Nara, R., Lin, Y.C., Nozawa, Y., Ng, Y., Itoh, G., Torii, O., Matsui, Y.: Revisiting relevance feedback for clip-based interactive image retrieval. arXiv preprint arXiv:2404.16398 (2024)"},{"key":"16_CR35","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H.V., Szafraniec, M., Khalidov, V., Fernandez, P., HAZIZA, D., Massa, F., El-Nouby, A., Assran, M., Ballas, N., Galuba, W., Howes, R., Huang, P.Y., Li, S.W., Misra, I., Rabbat, M., Sharma, V., Synnaeve, G., Xu, H., Jegou, H., Mairal, J., Labatut, P., Joulin, A., Bojanowski, P.: DINOv2: Learning robust visual features without supervision. Transactions on Machine Learning Research (2024)"},{"key":"16_CR36","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: International conference on machine learning (2021)"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"16_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. International Journal of Computer Vision (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"16_CR39","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C.W., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., Schramowski, P., Kundurthy, S.R., Crowson, K., Schmidt, L., Kaczmarczyk, R., Jitsev, J.: LAION-5b: An open large-scale dataset for training next generation image-text models. In: Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022)"},{"key":"16_CR40","unstructured":"Shen, K., Guo, J., Tan, X., Tang, S., Wang, R., Bian, J.: A study on relu and softmax in transformer. arXiv preprint arXiv:2302.06461 (2023)"},{"key":"16_CR41","unstructured":"Tao, Y., Takagi, K., Nakata, K.: Clustering-friendly representation learning via instance discrimination and feature decorrelation. In: International Conference on Learning Representations (2020)"},{"key":"16_CR42","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International conference on machine learning. pp. 10347\u201310357. PMLR (2021)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Georgoulis, S., Proesmans, M., Van\u00a0Gool, L.: Scan: Learning to classify images without labels. In: European Conference on Computer Vision. pp. 268\u2013285 (2020)","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"16_CR44","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, Z., Wang, X., Shen, C., Cheng, B., Shen, H., Xia, H.: End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"16_CR46","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., brian ichter, Xia, F., Chi, E.H., Le, Q.V., Zhou, D.: Chain of thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Stella, X.Y., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"16_CR48","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: Simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR49","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International conference on machine learning. pp. 478\u2013487. PMLR (2016)"},{"key":"16_CR50","unstructured":"Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., Gao, J.: Focal self-attention for local-global interactions in vision transformers. arXiv preprint arXiv:2107.00641 (2021)"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Yang, L., Cheung, N.M., Li, J., Fang, J.: Deep clustering by gaussian mixture variational autoencoders with graph embedding. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6440\u20136449 (2019)","DOI":"10.1109\/ICCV.2019.00654"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Yang, X., Deng, C., Zheng, F., Yan, J., Liu, W.: Deep spectral clustering using dual autoencoder network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4066\u20134075 (2019)","DOI":"10.1109\/CVPR.2019.00419"},{"key":"16_CR53","unstructured":"Zhai, S., Likhomanenko, T., Littwin, E., Busbridge, D., Ramapuram, J., Zhang, Y., Gu, J., Susskind, J.M.: Stabilizing transformer training by preventing attention entropy collapse. In: International Conference on Machine Learning. pp. 40770\u201340803. PMLR (2023)"},{"key":"16_CR54","unstructured":"Zhou, X., Zhang, N.L.: Deep clustering with features from self-supervised pretraining. arXiv preprint arXiv:2207.13364 (2022)"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., Yu, Z., Guo, Y.C., Li, Y., Liang, D., Cao, Y.P., Zhang, S.H.: Triplane meets gaussian splatting: Fast and generalizable single-view 3d reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10324\u201310335 (June 2024)","DOI":"10.1109\/CVPR52733.2024.00983"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0885-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T08:11:11Z","timestamp":1733472671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0885-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819608843","9789819608850"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0885-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}