Segmenting Known Objects and Unseen Unknowns without Prior Knowledge

TL;DR

This paper introduces holistic segmentation, a new approach that identifies and separates unseen, unknown objects in images without prior knowledge, enhancing robustness in real-world scenarios.

Contribution

It proposes U3HS, the first method to perform panoptic segmentation of known and unknown objects without prior unknown category data, addressing a key gap in robustness.

Findings

U3HS effectively detects unknown objects as uncertain regions.

Clustering embeddings enables accurate instance separation of unknowns.

Experiments show superior performance on COCO, Cityscapes, and Lost&Found datasets.

Abstract

Panoptic segmentation methods assign a known class to each pixel given in input. Even for state-of-the-art approaches, this inevitably enforces decisions that systematically lead to wrong predictions for objects outside the training categories. However, robustness against out-of-distribution samples and corner cases is crucial in safety-critical settings to avoid dangerous consequences. Since real-world datasets cannot contain enough data points to adequately sample the long tail of the underlying distribution, models must be able to deal with unseen and unknown scenarios as well. Previous methods targeted this by re-identifying already-seen unlabeled objects. In this work, we propose the necessary step to extend segmentation with a new setting which we term holistic segmentation. Holistic segmentation aims to identify and separate objects of unseen, unknown categories into instances without any prior knowledge about them while performing panoptic segmentation of known classes. We tackle this new problem with U3HS, which finds unknowns as highly uncertain regions and clusters their corresponding instance-aware embeddings into individual objects. By doing so, for the first time in panoptic segmentation with unknown objects, our U3HS is trained without unknown categories, reducing assumptions and leaving the settings as unconstrained as in real-life scenarios. Extensive experiments on public data from MS COCO, Cityscapes, and Lost&Found demonstrate the effectiveness of U3HS for this new, challenging, and assumptions-free setting called holistic segmentation. Project page: https://holisticseg.github.io.