{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:17:26Z","timestamp":1763018246308,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T00:00:00Z","timestamp":1601596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["G078618N"],"award-info":[{"award-number":["G078618N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"\u200bSwiss National Science Foundation","doi-asserted-by":"publisher","award":["#176004"],"award-info":[{"award-number":["#176004"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Research Council Advanced Grant","award":["#788506"],"award-info":[{"award-number":["#788506"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>This paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composable representations from input images and discrete labels. The obtained representations are based on distance estimates between the distributions given by the class label and those given by contextual information, which are modeled as environments. We prove that the representations have a clear structure allowing decomposing the representation into factors that represent classes and environments. We evaluate our novel technique on classification and retrieval tasks involving different modalities (visual and language data). In various experiments, we show how the representations can be compressed and how different hyperparameters impact performance.<\/jats:p>","DOI":"10.3390\/computers9040079","type":"journal-article","created":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T09:39:25Z","timestamp":1601631565000},"page":"79","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Structured (De)composable Representations Trained with Neural Networks"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5490-4879","authenticated-orcid":false,"given":"Graham","family":"Spinks","sequence":"first","affiliation":[{"name":"Departement Computerwetenschappen, Celestijnenlaan 200a\u2014bus 2402, 3001 Leuven, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3732-9323","authenticated-orcid":false,"given":"Marie-Francine","family":"Moens","sequence":"additional","affiliation":[{"name":"Departement Computerwetenschappen, Celestijnenlaan 200a\u2014bus 2402, 3001 Leuven, Belgium"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1037\/0033-295X.89.6.609","article-title":"A theory for the storage and retrieval of item and associative information","volume":"89","author":"Murdock","year":"1982","journal-title":"Psychol. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1080\/09658210244000216","article-title":"The myth of the encoding-retrieval match","volume":"10","author":"Nairne","year":"2002","journal-title":"Memory"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"121","DOI":"10.3389\/fncir.2018.00121","article-title":"A framework for intelligence and cortical function based on grid cells in the neocortex","volume":"12","author":"Hawkins","year":"2019","journal-title":"Front. Neural Circuits"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term-weighting approaches in automatic text retrieval","volume":"24","author":"Salton","year":"1988","journal-title":"Inf. Process. Manag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Robertson, S., and Walker, S. (1994, January 3\u20136). Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval. Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Dublin, Ireland.","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"ref_6","unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., and Zettlemoyer, L. (2018, January 1\u20136). Deep Contextualized Word Representations. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, LA, USA.","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref_8","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","article-title":"Indexing by latent semantic analysis","volume":"41","author":"Deerwester","year":"1990","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"ref_10","unstructured":"Singh, S.P., Hug, A., Dieuleveut, A., and Jaggi, M. (2019, January 6\u20139). Context Mover\u2019s Distance & Barycenters: Optimal transport of contexts for building representations. Proceedings of the ICLR Workshop on Deep Generative Models, New Orleans, LA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1002\/sapm1941201224","article-title":"The distribution of a product from several sources to numerous localities","volume":"20","author":"Hitchcock","year":"1941","journal-title":"J. Math. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1023\/A:1026543900054","article-title":"The earth mover\u2019s distance as a metric for image retrieval","volume":"40","author":"Rubner","year":"2000","journal-title":"Int. J. Comput. Vis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1214\/aoms\/1177703591","article-title":"A relationship between arbitrary positive matrices and doubly stochastic matrices","volume":"35","author":"Sinkhorn","year":"1964","journal-title":"Ann. Math. Stat."},{"key":"ref_14","unstructured":"Altschuler, J., Niles-Weed, J., and Rigollet, P. (2017, January 4\u20139). Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration. Proceedings of the Advances in Neural Information Processing Systems 30, Long Beach, CA, USA."},{"key":"ref_15","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein Generative Adversarial Networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_16","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A.C. (2017, January 4\u20139). Improved training of wasserstein gans. Proceedings of the Advances in Neural Information Processing Systems 30, Long Beach, CA, USA."},{"key":"ref_17","unstructured":"Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (May, January 30). Spectral Normalization for Generative Adversarial Networks. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_18","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems 28, Montreal, QC, Canada."},{"key":"ref_19","unstructured":"Kusner, M., Sun, Y., Kolkin, N., and Weinberger, K. (2015, January 6\u201311). From Word Embeddings to Document Distances. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1007\/s10994-018-5717-1","article-title":"Wasserstein discriminant analysis","volume":"107","author":"Flamary","year":"2018","journal-title":"Mach. Learn."},{"key":"ref_21","first-page":"1","article-title":"Extensions of Lipschitz mappings into a Hilbert space","volume":"26","author":"Johnson","year":"1984","journal-title":"Contemp. Math."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/TIT.2005.862083","article-title":"Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information","volume":"52","author":"Romberg","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"Donoho","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_24","unstructured":"Rahimi, A., and Recht, B. (2008, January 8\u201313). Random features for large-scale kernel machines. Proceedings of the Advances in Neural Information Processing Systems 21, Vancouver, BC, Canada."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wu, L., Yen, I.E., Xu, K., Xu, F., Balakrishnan, A., Chen, P.Y., Ravikumar, P., and Witbrock, M.J. (November, January 31). Word Mover\u2019s Embedding: From Word2Vec to Document Embedding. Proceedings of the 2018 Conference on EMNLP, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1482"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e7","DOI":"10.23915\/distill.00007","article-title":"Feature visualization","volume":"2","author":"Olah","year":"2017","journal-title":"Distill"},{"key":"ref_27","unstructured":"Spinks, G., and Moens, M.F. (November, January 31). Evaluating textual representations through image generation. Proceedings of the Workshop on Analyzing and Interpreting Neural Networks for NLP, EMNLP, Brussels, Belgium."},{"key":"ref_28","unstructured":"Zagoruyko, S., and Komodakis, N. (2016). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv."},{"key":"ref_29","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., and Lerchner, A. (2017, January 24\u201326). Beta-vae: Learning basic visual concepts with a constrained variational framework. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_30","unstructured":"Pandey, A., Fanuel, M., Schreurs, J., and Suykens, J.A. (2020). Disentangled Representation Learning and Generation with Manifold Optimization. arXiv."},{"key":"ref_31","unstructured":"Mroueh, Y., and Sercu, T. (2017, January 4\u20139). Fisher gan. Proceedings of the Advances in Neural Information Processing Systems 30, Long Beach, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Rahimi, A., and Recht, B. (2008, January 23\u201326). Uniform approximation of functions with random bases. Proceedings of the 2008 46th Annual Allerton Conference on Communication, Control, and Computing, Urbana-Champaign, IL, USA.","DOI":"10.1109\/ALLERTON.2008.4797607"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft coco: Common objects in context. Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_34","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_35","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (July, January 26). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_36","first-page":"1","article-title":"A literature survey on algorithms for multi-label learning","volume":"18","author":"Sorower","year":"2010","journal-title":"Or. State Univ. Corvallis"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Costa Pereira, J., Coviello, E., Doyle, G., Lanckriet, G.R., Levy, R., and Vasconcelos, N. (2010, January 25\u201329). A new approach to cross-modal multimedia retrieval. Proceedings of the 18th ACM International Conference on Multimedia, Firenze, Italy.","DOI":"10.1145\/1873951.1873987"},{"key":"ref_38","unstructured":"Yang, Z., Dai, Z., Salakhutdinov, R., and Cohen, W.W. (May, January 30). Breaking the Softmax Bottleneck: A High-Rank RNN Language Model. Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_39","unstructured":"Press, W.H., Teukolsky, S.A., Vetterling, W.T., and Flannery, B.P. (2007). Numerical Recipes 3rd Edition: The Art of Scientific Computing, Cambridge University Press."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/9\/4\/79\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:16:03Z","timestamp":1760177763000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/9\/4\/79"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,2]]},"references-count":39,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["computers9040079"],"URL":"https:\/\/doi.org\/10.3390\/computers9040079","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2020,10,2]]}}}