Temporal Output Discrepancy for Loss Estimation-based Active Learning

TL;DR

This paper introduces a novel active learning method using Temporal Output Discrepancy (TOD) to estimate sample loss, enabling efficient data annotation and achieving superior results in image classification and segmentation tasks.

Contribution

The paper proposes TOD, a simple and task-agnostic measure for active learning that effectively estimates sample loss and improves data selection strategies.

Findings

Outperforms state-of-the-art active learning methods on image classification.

Effective in semantic segmentation tasks.

Can select the best model from multiple candidates.

Abstract

While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset. Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss. The core of our approach is a measurement Temporal Output Discrepancy (TOD) that estimates the sample loss by evaluating the discrepancy of outputs given by models at different optimization steps. Our theoretical investigation shows that TOD lower-bounds the accumulated sample loss thus it can be used to select informative unlabeled samples. On basis of TOD, we further develop an effective unlabeled data sampling strategy as well as an unsupervised learning criterion for active learning. Due to the simplicity of TOD, our methods are efficient, flexible, and task-agnostic. Extensive experimental results demonstrate that our approach achieves superior performances than the state-of-the-art active learning methods on image classification and semantic segmentation tasks. In addition, we show that TOD can be utilized to select the best model of potentially the highest testing accuracy from a pool of candidate models.