Deep Active Learning with Manifold-preserving Trajectory Sampling

TL;DR

This paper introduces Manifold-Preserving Trajectory Sampling (MPTS), a novel active learning method that reduces bias in data selection by aligning feature space distributions, leading to improved model performance across vision and non-vision datasets.

Contribution

The paper proposes MPTS, a new active learning approach that enforces manifold preservation in feature space to correct bias from labeled data, enhancing data selection quality.

Findings

MPTS outperforms existing active learning methods on multiple benchmarks.

The method effectively reduces bias in data selection.

Experimental results show significant performance improvements.

Abstract

Active learning (AL) is for optimizing the selection of unlabeled data for annotation (labeling), aiming to enhance model performance while minimizing labeling effort. The key question in AL is which unlabeled data should be selected for annotation. Existing deep AL methods arguably suffer from bias incurred by clabeled data, which takes a much lower percentage than unlabeled data in AL context. We observe that such an issue is severe in different types of data, such as vision and non-vision data. To address this issue, we propose a novel method, namely Manifold-Preserving Trajectory Sampling (MPTS), aiming to enforce the feature space learned from labeled data to represent a more accurate manifold. By doing so, we expect to effectively correct the bias incurred by labeled data, which can cause a biased selection of unlabeled data. Despite its focus on manifold, the proposed method can be conveniently implemented by performing distribution mapping with MMD (Maximum Mean Discrepancies). Extensive experiments on various vision and non-vision benchmark datasets demonstrate the superiority of our method. Our source code can be found here.