Novel Class Discovery in Semantic Segmentation

TL;DR

This paper introduces a new setting for semantic segmentation called NCDSS, which focuses on discovering and segmenting novel classes in unlabeled images using prior knowledge, and proposes a framework with uncertainty modeling to improve performance.

Contribution

It presents the first approach for novel class discovery in semantic segmentation and introduces the EUMS framework to handle noisy pseudo-labels effectively.

Findings

Achieved 49.81% mIoU on PASCAL-5i dataset with the basic framework.

EUMS framework outperforms the basic framework by 9.28% mIoU.

Built the NCDSS benchmark on PASCAL-5i and COCO-20i datasets.

Abstract

We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In contrast to existing approaches that look at novel class discovery in image classification, we focus on the more challenging semantic segmentation. In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image, which increases the difficulty in using the unlabeled data. To tackle this new setting, we leverage the labeled base data and a saliency model to coarsely cluster novel classes for model training in our basic framework. Additionally, we propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels, further improving the model performance on the novel classes. Our EUMS utilizes an entropy ranking technique and a dynamic reassignment to distill clean labels, thereby making full use of the noisy data via self-supervised learning. We build the NCDSS benchmark on the PASCAL-5$^i$ dataset and COCO-20$^i$ dataset. Extensive experiments demonstrate the feasibility of the basic framework (achieving an average mIoU of 49.81% on PASCAL-5$^i$) and the effectiveness of EUMS framework (outperforming the basic framework by 9.28% mIoU on PASCAL-5$^i$).