Revisiting Deep Active Learning for Semantic Segmentation

Abstract

Active learning automatically selects samples for annotation from a data pool to achieve maximum performance with minimum annotation cost. This is particularly critical for semantic segmentation, where annotations are costly. In this work, we show in the context of semantic segmentation that the data distribution is decisive for the performance of the various active learning objectives proposed in the literature. Particularly, redundancy in the data, as it appears in most driving scenarios and video datasets, plays a large role. We demonstrate that the integration of semisupervised learning with active learning can improve performance when the two objectives are aligned. Our experimental study shows that current active learning benchmarks for segmentation in driving scenarios are not realistic since they operate on data that is already curated for maximum diversity. Accordingly, we propose a more realistic evaluation scheme in which the value of active learning becomes clearly visible, both by itself and in combination with semisupervised learning.

An innovative deep active learning approach for improving unlabeled audio classification by selectively querying informative instance

“…This strategy selects which instances from the unlabeled pool should be queried for annotation at each iteration based on the informativeness of each instance -how useful labeling that instance is expected to be for improving the classifier's performance. 16 The goal is to query the most valuable instances to maximize the impact of each obtained label.…”

Enhancing Semantic Segmentation through Reinforced Active Learning: Combating Dataset Imbalances and Bolstering Annotation Efficiency

“…Recent active learning work has also looked at semantic segmentation [60] . Uncertainty-driven active learning identifies data samples with elevated aleatoric uncertainty.…”