Unsupervised Object Learning via Common Fate

Matthias Tangemann, Steffen Schneider, Julius Von Kügelgen, Francesco Locatello, Peter Vincent Gehler, Thomas Brox, Matthias Kuemmerer, Matthias Bethge, Bernhard Schölkopf

Keywords: object learning, scene modeling, scene generation, causal modeling, causal representation learning, generative modeling, common fate

TL;DR: 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.

Abstract: Learning generative object models from unlabelled videos is a long standing problem and 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 learns generative models that generalize beyond occlusions present in the input videos and represents scenes in a modular fashion, allowing generation of plausible scenes outside the training distribution by permitting, for instance, object numbers or densities not observed during training.

Community Implementations: [ 7 code implementations](https://www.catalyzex.com/paper/arxiv:2110.06562/code)