{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:17:18Z","timestamp":1743081438220,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732287"},{"type":"electronic","value":"9783031732294"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-73229-4_6","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T15:03:09Z","timestamp":1729782189000},"page":"88-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Plausibility Evaluation for\u00a0Generated Designs with\u00a0Denoising Autoencoder"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1825-5099","authenticated-orcid":false,"given":"Jiajie","family":"Fan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7613-9872","authenticated-orcid":false,"given":"Amal","family":"Trigui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6768-1478","authenticated-orcid":false,"given":"Thomas","family":"B\u00e4ck","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4933-5181","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Aubry, M., Maturana, D., Efros, A.A., Russell, B.C., Sivic, J.: Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models. In: 2014 IEEE CVPR, pp. 3762\u20133769 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.487","DOI":"10.1109\/CVPR.2014.487"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Baker, N., Lu, H., Erlikhman, G., Kellman, P.J.: Deep convolutional networks do not classify based on global object shape. PLoS Comput. Biol. 14 (2018). https:\/\/api.semanticscholar.org\/CorpusID:54476941","DOI":"10.1371\/journal.pcbi.1006613"},{"key":"6_CR3","unstructured":"Barratt, S.T., Sharma, R.: A note on the inception score. ArXiv abs\/1801.01973 (2018). https:\/\/api.semanticscholar.org\/CorpusID:38384342"},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Betzalel, E., Penso, C., Navon, A., Fetaya, E.: A study on the evaluation of generative models. CoRR abs\/2206.10935 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.10935","DOI":"10.48550\/ARXIV.2206.10935"},{"key":"6_CR5","unstructured":"Binkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=r1lUOzWCW"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Borji, A.: Pros and cons of GAN evaluation measures: new developments. Comput. Vis. Image Underst. 215, 103329 (2022). https:\/\/doi.org\/10.1016\/j.cviu.2021.103329, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314221001685","DOI":"10.1016\/j.cviu.2021.103329"},{"key":"6_CR7","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. ArXiv abs\/1809.11096 (2018), https:\/\/api.semanticscholar.org\/CorpusID:52889459"},{"key":"6_CR8","doi-asserted-by":"publisher","first-page":"103768","DOI":"10.1016\/j.cviu.2023.103768","volume":"235","author":"LF Buzuti","year":"2023","unstructured":"Buzuti, L.F., Thomaz, C.E.: Fr\u00e9chet autoencoder distance: a new approach for evaluation of generative adversarial networks. Comput. Vis. Image Underst. 235, 103768 (2023)","journal-title":"Comput. Vis. Image Underst."},{"key":"6_CR9","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS 2020, Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: diverse image synthesis for multiple domains. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8185\u20138194 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00821","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"6_CR11","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: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 248\u2013255. IEEE (2009). https:\/\/ieeexplore.ieee.org\/abstract\/document\/5206848\/","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR12","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat GANs on image synthesis. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=AAWuCvzaVt"},{"key":"6_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"6_CR14","unstructured":"Fan, J., Vuaille, L., B\u00e4ck, T., Wang, H.: On the noise scheduling for generating plausible designs with diffusion models (2023)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Fan, J., Vuaille, L., Wang, H., B\u00e4ck, T.: Adversarial latent autoencoder with self-attention for structural image synthesis. arXiv preprint arXiv:2307.10166 (2023)","DOI":"10.1109\/CAI59869.2024.00030"},{"key":"6_CR16","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F., Brendel, W.: Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. ArXiv abs\/1811.12231 (2018). https:\/\/api.semanticscholar.org\/CorpusID:54101493"},{"key":"6_CR17","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014). http:\/\/papers.nips.cc\/paper\/5423-generative-adversarial-nets.pdf"},{"issue":"1","key":"6_CR18","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton, A., Borgwardt, K.M., Rasch, M.J., Sch\u00f6lkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(1), 723\u2013773 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR20","unstructured":"Hermann, K.L., Chen, T., Kornblith, S.: The origins and prevalence of texture bias in convolutional neural networks. arXiv: Computer Vision and Pattern Recognition (2019). https:\/\/api.semanticscholar.org\/CorpusID:220266152"},{"key":"6_CR21","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: Advances in Neural Information Processing Systems, vol. 30 (NIPS 2017) (2018)"},{"key":"6_CR22","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arxiv:2006.11239 (2020)"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Horak, D., Yu, S., Khorshidi, G.S.: Topology distance: a topology-based approach for evaluating generative adversarial networks. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 7721\u20137728. AAAI Press (2021). https:\/\/doi.org\/10.1609\/AAAI.V35I9.16943","DOI":"10.1609\/AAAI.V35I9.16943"},{"key":"6_CR24","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. ArXiv abs\/1710.10196 (2017). https:\/\/api.semanticscholar.org\/CorpusID:3568073"},{"key":"6_CR25","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Kucker, S.C., et al.: Reproducibility and a unifying explanation: lessons from the shape bias. Infant Behav. Dev. 54, 156\u2013165 (2019). https:\/\/api.semanticscholar.org\/CorpusID:53045726","DOI":"10.1016\/j.infbeh.2018.09.011"},{"key":"6_CR28","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Aittala, M., Aila, T., Lehtinen, J.: The role of imagenet classes in fr\u00e9chet inception distance. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=4oXTQ6m_ws8"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Landau, B., Smith, L.B., Jones, S.S.: The importance of shape in early lexical learning. Cogn. Dev. 3, 299\u2013321 (1988). https:\/\/api.semanticscholar.org\/CorpusID:205117480","DOI":"10.1016\/0885-2014(88)90014-7"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: Towards visually explaining variational autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8642\u20138651 (2020)","DOI":"10.1109\/CVPR42600.2020.00867"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Maiorca, A., Yoon, Y., Dutoit, T.: Evaluating the quality of a synthesized motion with the fr\u00e9chet motion distance. In: ACM SIGGRAPH 2022 Posters. SIGGRAPH 2022, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3532719.3543228","DOI":"10.1145\/3532719.3543228"},{"key":"6_CR33","unstructured":"Naeem, M.F., Oh, S.J., Uh, Y., Choi, Y., Yoo, J.: Reliable fidelity and diversity metrics for generative models. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0119, pp. 7176\u20137185. PMLR (2020). https:\/\/proceedings.mlr.press\/v119\/naeem20a.html"},{"key":"6_CR34","unstructured":"Nobari, A.H., Rashad, M.F., Ahmed, F.: Creativegan: editing generative adversarial networks for creative design synthesis. CoRR abs\/2103.06242 (2021). https:\/\/arxiv.org\/abs\/2103.06242"},{"key":"6_CR35","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"6_CR36","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"6_CR37","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings (2016). http:\/\/arxiv.org\/abs\/1511.06434"},{"key":"6_CR38","doi-asserted-by":"publisher","unstructured":"Regenwetter, L., Curry, B., Ahmed, F.: BIKED: a dataset for computational bicycle design with machine learning benchmarks. J. Mech. Des. 144(3) (2021). https:\/\/doi.org\/10.1115\/1.4052585","DOI":"10.1115\/1.4052585"},{"issue":"7","key":"6_CR39","doi-asserted-by":"publisher","first-page":"071704","DOI":"10.1115\/1.4053859","volume":"144","author":"L Regenwetter","year":"2022","unstructured":"Regenwetter, L., Nobari, A.H., Ahmed, F.: Deep generative models in engineering design: a review. J. Mech. Des. 144(7), 071704 (2022)","journal-title":"J. Mech. Des."},{"key":"6_CR40","unstructured":"Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. ArXiv abs\/1606.03498 (2016), https:\/\/api.semanticscholar.org\/CorpusID:1687220"},{"key":"6_CR41","doi-asserted-by":"publisher","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"6_CR42","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502 (2020). https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"6_CR43","doi-asserted-by":"publisher","unstructured":"Stein, G., et al.: Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models. CoRR abs\/2306.04675 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2306.04675","DOI":"10.48550\/ARXIV.2306.04675"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2818\u20132826 (2015). https:\/\/api.semanticscholar.org\/CorpusID:206593880","DOI":"10.1109\/CVPR.2016.308"},{"key":"6_CR45","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: International Conference on Machine Learning (2008). https:\/\/api.semanticscholar.org\/CorpusID:207168299","DOI":"10.1145\/1390156.1390294"},{"key":"6_CR47","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. ArXiv abs\/1708.07747 (2017). https:\/\/api.semanticscholar.org\/CorpusID:702279"},{"key":"6_CR48","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 586\u2013595. Computer Vision Foundation \/ IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068, http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/ Zhang_The_Unreasonable_Effectiveness_CVPR_2018_paper.html","DOI":"10.1109\/CVPR.2018.00068"},{"key":"6_CR49","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"W Zhou","year":"2004","unstructured":"Zhou, W.: Image quality assessment: from error measurement to structural similarity. IEEE Trans. Image Process. 13, 600\u2013613 (2004)","journal-title":"IEEE Trans. Image Process."}],"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\/978-3-031-73229-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T15:03:55Z","timestamp":1729782235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73229-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031732287","9783031732294"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73229-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 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"}}]}}