Test-time adaptation with slot-centric models

TLDR: Current SOTA methods for scene understanding, though impressive, often fail to decompose out-of-distribution scenes. Problem Statement: In machine learning, we often assume the train and test split are IID samples from the same distribution. In fact, there is a distribution shift happening all the time! For example on the left, we visualize images from the ImageNet Chair category, and on the right, we visualize the ObjectNet chair category. As you can see there are a variety of real-world distribution shifts happening all the time.