Active Learning for Semantic Segmentation with Multi-class Label Query

TL;DR

This paper introduces a novel active learning approach for semantic segmentation that uses multi-class region queries, improving annotation efficiency and accuracy through a two-stage disambiguation process.

Contribution

It presents a new multi-class region query strategy combined with a two-stage label disambiguation algorithm, enhancing annotation efficiency and segmentation performance.

Findings

Outperforms previous methods on Cityscapes and PASCAL VOC 2012 datasets.

Reduces annotation cost while maintaining high segmentation accuracy.

Introduces a new acquisition function for multi-class labeling.

Abstract

This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an oracle for a multi-hot vector indicating all classes existing in the region. This multi-class labeling strategy is substantially more efficient than existing ones like segmentation, polygon, and even dominant class labeling in terms of annotation time per click. However, it introduces the class ambiguity issue in training as it assigns partial labels (i.e., a set of candidate classes) to individual pixels. We thus propose a new algorithm for learning semantic segmentation while disambiguating the partial labels in two stages. In the first stage, it trains a segmentation model directly with the partial labels through two new loss functions motivated by partial label learning and multiple instance learning. In the second stage, it disambiguates the partial labels by generating pixel-wise pseudo labels, which are used for supervised learning of the model. Equipped with a new acquisition function dedicated to the multi-class labeling, our method outperforms previous work on Cityscapes and PASCAL VOC 2012 while spending less annotation cost. Our code and results are available at https://github.com/sehyun03/MulActSeg.