SPOT: An Active Learning Algorithm for Efficient Deep Neural Network Training

Luyang Fang

doi:10.26599/BDMA.2025.9020011

SPOT: An Active Learning Algorithm for Efficient Deep Neural Network Training

2025-10-01

1

PRE

AI

DOI：10.26599/BDMA.2025.9020011

Original

Original request for help

Save

Abstract

En 中文

Recent advancements in deep neural networks heavily rely on large-scale labeled datasets. However, acquiring annotations for large datasets can be challenging due to annotation constraints. Active learning offers a promising solution to this problem by selectively labeling a small, strategically chosen subset of the unlabeled dataset. However, current active learning methods struggle with data that are unevenly distributed, which leads to the selection of subsets that fail to represent the entire dataset. To overcome this challenge, we introduce a novel active learning algorithm that integrates SPace-filling (SP) designs with the Optimal Transport (OT) technique (SPOT). SPOT technique utilizes optimal transport to effectively manage data from complex manifolds by mapping them to a uniformly distributed hypercube. Additionally, the spacefilling design ensures a better asymptotic convergence rate, ensuring that the selected subset encompasses the entire dataset more effectively than other sampling methods, such as random sampling. Our extensive experiments across various image datasets and models demonstrate the superiority of SPOT over existing baselines.

Keywords:

Active Learning (AL)

Optimal Transport (OT)

SPace-filling (SP)

sampling

deep learning

Active Learning (AL)

Optimal Transport (OT)

SPace-filling (SP)

sampling

deep learning

SPOT: An Active Learning Algorithm for Efficient Deep Neural Network Training

Abstract

Journal

Organization