Unsupervised Object Learning via Common FateDownload PDF

Published: 28 Jan 2022, Last Modified: 22 Oct 2023ICLR 2022 SubmittedReaders: Everyone
Keywords: object learning, scene modeling, scene generation, causal modeling, causal representation learning, generative modeling, common fate
Abstract: Learning generative object models from unlabelled videos is a long standing problem and is required for causal scene modeling. We decompose this problem into three easier subtasks, and provide candidate solutions for each of them. Inspired by the Common Fate Principle of Gestalt Psychology, we first extract (noisy) masks of moving objects via unsupervised motion segmentation. Second, generative models are trained on the masks of the background and the moving objects, respectively. Third, background and foreground models are combined in a conditional ``dead leaves scene model to sample novel scene configurations where occlusions and depth layering arise naturally. To evaluate the individual stages, we introduce the Fishbowl dataset positioned between complex real-world scenes and common object-centric benchmarks of simplistic objects. We show that our approach allows learning generative models that generalize beyond the occlusions present in the input videos, and represent scenes in a modular fashion that allows sampling plausible scenes outside the training distribution by permitting, for instance, object numbers or densities not observed in the training set.
One-sentence Summary: We propose a multi-stage approach for learning object, background and scene models based on unsupervised motion segmentation that allows controlled scene generation beyond the training distribution.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 7 code implementations](https://www.catalyzex.com/paper/arxiv:2110.06562/code)
15 Replies

Loading