Rotating features for object discovery

conference paper Rotating features for object discovery Advances in Neural Information Processing Systems published yes Sindy Löwe author Phillip Lippe author Francesco Locatello author 26cfd52f-2483-11ee-8040-88983bcc06d40000-0002-4850-0683 Max Welling author FrLo department NeurIPS: Neural Information Processing Systems The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing this issue in an unsupervised setting have focused on slot-based methods, which may be limiting due to their discrete nature and difficulty to express uncertainty. Recently, the Complex AutoEncoder was proposed as an alternative that learns continuous and distributed object-centric representations. However, it is only applicable to simple toy data. In this paper, we present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations. Additionally, we show the applicability of our approach to pre-trained features. Together, these advancements enable us to scale distributed object-centric representations from simple toy to real-world data. We believe this work advances a new paradigm for addressing the binding problem in machine learning and has the potential to inspire further innovation in the field. https://research-explorer.ista.ac.at/download/14207/22603/2026_Neurips_Loewe.pdf application/pdfno Neural Information Processing Systems Foundation2023New Orleans, LA, United States eng 37th Conference on Neural Information Processing Systems 1049-5258 2306.00600 36 Löwe, S., Lippe, P., Locatello, F., & Welling, M. (2023). Rotating features for object discovery. In 37th Conference on Neural Information Processing Systems (Vol. 36). New Orleans, LA, United States: Neural Information Processing Systems Foundation. S. Löwe, P. Lippe, F. Locatello, and M. Welling, “Rotating features for object discovery,” in 37th Conference on Neural Information Processing Systems, New Orleans, LA, United States, 2023, vol. 36. Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery. In: 37th Conference on Neural Information Processing Systems. Vol 36. Neural Information Processing Systems Foundation; 2023. Löwe, Sindy, Phillip Lippe, Francesco Locatello, and Max Welling. “Rotating Features for Object Discovery.” In 37th Conference on Neural Information Processing Systems, Vol. 36. Neural Information Processing Systems Foundation, 2023. Löwe, Sindy, et al. “Rotating Features for Object Discovery.” 37th Conference on Neural Information Processing Systems, vol. 36, Neural Information Processing Systems Foundation, 2023. S. Löwe, P. Lippe, F. Locatello, M. Welling, in:, 37th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2023. Löwe S, Lippe P, Locatello F, Welling M. 2023. Rotating features for object discovery. 37th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 36. 142072023-08-22T14:18:00Z2026-07-29T07:36:23Z