{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:53:53Z","timestamp":1762509233899,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732010"},{"type":"electronic","value":"9783031732027"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73202-7_26","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:16:32Z","timestamp":1732112192000},"page":"449-464","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Assessing Sample Quality via\u00a0the\u00a0Latent Space of\u00a0Generative Models"],"prefix":"10.1007","author":[{"given":"Jingyi","family":"Xu","sequence":"first","affiliation":[]},{"given":"Hieu","family":"Le","sequence":"additional","affiliation":[]},{"given":"Dimitris","family":"Samaras","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13104-019-4121-7","volume":"12","author":"A Aksac","year":"2019","unstructured":"Aksac, A., Demetrick, D.J., Reda Alhajj, T.O.: BreCaHAD: a dataset for breast cancer histopatholog- ical annotation and diagnosis. BMC. Res. Notes 12, 1\u20133 (2019)","journal-title":"BMC. Res. Notes"},{"key":"26_CR2","unstructured":"Azadi, S., Olsson, C., Darrell, T., Goodfellow, I., Odena, A.: Discriminator rejection sampling. In: ArXiv (2019)"},{"key":"26_CR3","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton., A.: Demystifying MMD GANs. In: ICLR (2018)"},{"key":"26_CR4","unstructured":"Branwen, G., Anonymous, Community., D.: Danbooru2019 portraits: a large-scale anime head illus- tration dataset (2019). https:\/\/www.gwern.net\/crops#danbooru2019-portraits"},{"key":"26_CR5","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin., A.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"26_CR7","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, Z., Xu, H., Darrell, T., Wang, X.: Meta-baseline: exploring simple meta-learning for few-shot learning. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: diverse image synthesis for multiple domains. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"26_CR10","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. TPAMI 24, 603\u2013619 (2002)","journal-title":"TPAMI"},{"key":"26_CR11","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"26_CR12","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. In: NeurIPS (2014)"},{"key":"26_CR13","unstructured":"Han, J., Choi, H., Choi, Y., Kim, J., Ha, J.W., Choi, J.: Rarity score : a new metric to evaluate the uncommonness of synthesized images. In: ICLR (2023)"},{"key":"26_CR14","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter., S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"26_CR15","unstructured":"Ho, J., Salimans., T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"26_CR16","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: NeurIPS (2020)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"26_CR19","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)"},{"key":"26_CR20","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: Generative flow with invertible 1x1 convolutions. In: NeurIPS (2018)"},{"key":"26_CR21","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Mimproved precision and recall metric for assessing generative models. In: NeurIPS (2019)"},{"key":"26_CR22","unstructured":"LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit databases. Technical report (2014)"},{"key":"26_CR23","unstructured":"Lee, J., Kim, H., Hong, Y., Chung, H.W.: Self-diagnosing GAN: diagnosing underrepresented samples in generative adversarial networks. In: NeurIPS (2021)"},{"key":"26_CR24","unstructured":"Li, S., Liu, C., Zhang, T., Le, H., S\u00fcsstrunk, S., Salzmann, M.: Controlling the fidelity and diversity of deep generative models via pseudo density (2024). https:\/\/arxiv.org\/abs\/2407.08659"},{"key":"26_CR25","unstructured":"Naeem, M.F., Oh, S.J., Uh, Y., Choi, Y., Yoo., J.: Reliable fidelity and diversity metrics for generative models. In: ICML (2020)"},{"key":"26_CR26","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv: abs\/2112.10741 (2021)"},{"key":"26_CR27","unstructured":"Oreshkin, B., Lop\u0301ez, P.R., Lacoste., A.: TADAM: task dependent adaptive metric for improved few-shot learning. In: NeurIPS (2018)"},{"key":"26_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"26_CR29","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen., M.: Hierarchical text- conditional image generation with clip latents. ArXiv abs\/2204.06125 (2022)"},{"key":"26_CR30","unstructured":"Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR32","unstructured":"Sajjadi, M.S.M., Bachem, O., Lucic, M., Bousquet, O., Gelly, S.: Assessing generative models via precision and recall. In: NeurIPS (2018)"},{"key":"26_CR33","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen., X.: Improved techniques for training GANs. In: NeurIPS (2016)"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of GANs for semantic face editing. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"26_CR36","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. In: NeurIPS (2020)"},{"key":"26_CR37","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS (2016)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"26_CR39","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H.: Generating representative samples for few-shot classification. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00880"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H., Huang, M., Athar, S., Samaras, D.: Variational feature disentangling for fine-grained few-shot classification. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00869"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H., Nguyen, V., Ranjan, V., Samaras, D.: Zero-shot object counting. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01492"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H., Samaras, D.: Generating features with increased crop-related diversity for few-shot object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01888"},{"key":"26_CR44","unstructured":"Yu, F., Zhang, Y., Song, S., Seff, A., Xiao., J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. CoRR (2015)"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, X.Y., Liu, Y., Wang, P.S., Tong, X.: SDF-styleGAN: implicit SDF-based styleGAN for 3D shape generation. In: SGP (2022)","DOI":"10.1111\/cgf.14602"},{"key":"26_CR46","unstructured":"Zhu, P., Abdal, R., Qin, Y., Femiani, J., Wonka, P.: Improved styleGAN embedding: where are the good latents? arXiv preprint arXiv:2012.09036 (2020)"}],"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\/978-3-031-73202-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:11:05Z","timestamp":1732115465000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 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"}}]}}