Temporally Consistent Object-Centric Learning by Contrasting Slots

TL;DR

This paper introduces a novel temporal contrastive loss for unsupervised object-centric learning from videos, significantly enhancing temporal consistency and object discovery, thereby improving downstream tasks like object dynamics prediction.

Contribution

The work proposes a new object-level temporal contrastive loss that enforces temporal consistency in unsupervised video object-centric models, leading to state-of-the-art results.

Findings

Improved temporal consistency of object representations.

Enhanced object discovery performance.

State-of-the-art results on synthetic and real-world datasets.

Abstract

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be both compositional and temporally consistent. Existing approaches based on recurrent processing often lack long-term stability across frames because their training objective does not enforce temporal consistency. In this work, we introduce a novel object-level temporal contrastive loss for video object-centric models that explicitly promotes temporal consistency. Our method significantly improves the temporal consistency of the learned object-centric representations, yielding more reliable video decompositions that facilitate challenging downstream tasks such as unsupervised object dynamics prediction. Furthermore, the inductive bias added by our loss strongly improves object discovery, leading to state-of-the-art results on both synthetic and real-world datasets, outperforming even weakly-supervised methods that leverage motion masks as additional cues.