Efficient Object-Centric Learning for Videos

Rickard Maus, Atsuto Maki

Keywords: Object-Centric Learning, Representation Learning, Video, Segmentation, Video Object Segmentation

TL;DR: We introduce a novel method for efficiently learning object-centric representations over videos and achieve state-of-the-art video object segmentation performance on YTVIS-19.

Abstract: This paper introduces a method for efficiently learning video-level object-centric representations by bootstrapping off a pre-trained image backbone, which we term Interpreter. It presents a novel hierarchical slot attention architecture with local learning and an optimal transport objective that yields fully unsupervised video segmentation. We first learn to compress images into image-level object-centric representations. Interpreter then learns to compress and reconstruct the object-centric representations for each frame across a video, allowing us to circumvent the costly process of reconstructing full frame feature maps. Unlike prior work, this allows us to scale to significantly longer videos without resorting to chunking videos into segments and matching between them. To deal with the unordered nature of object-centric representations, we employ Sinkhorn divergence, a relaxed optimal transport objective, to compute the distance between unordered sets of representations. We evaluate the resulting segmentation maps on video instance segmentation in both realistic and synthetic settings, using YTVIS-19 and MOVi-E, respectively. Interpreter achieves state-of-the-art results on the realistic YTVIS-19 dataset and presents a promising approach of scaling object-centric representation learning to longer videos.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10066