Self-supervised Object-Centric Learning for Videos

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Unsupervised Object Discovery, Unsupervised Video Object Segmentation, Object-Centric Learning, Unsupervised Video Multi Object Segmentation
TL;DR: In this paper, we introduce SOLV (Self-supervised Object-Centric Learning for Videos), a self-supervised model capable of discovering multiple objects in real-world video sequences without using additional modalities.
Abstract: Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the segmentation in video sequences. However, the performance improvements observed in synthetic sequences, which rely on the robustness of an additional cue, do not translate to more challenging real-world scenarios. In this paper, we propose the first fully unsupervised method for segmenting multiple objects in real-world sequences. Our object-centric learning framework spatially binds objects to slots on each frame and then relates these slots across frames. From these temporally-aware slots, the training objective is to reconstruct the middle frame in a high-level semantic feature space. We propose a masking strategy by dropping a significant portion of tokens in the feature space for efficiency and regularization. Additionally, we address over-clustering by merging slots based on similarity. Our method can successfully segment multiple instances of complex and high-variety classes in YouTube videos.
Supplementary Material: zip
Submission Number: 1052