Making Your First Choice: To Address Cold Start Problem in Vision Active Learning

TL;DR

This paper addresses the cold start problem in vision active learning by leveraging contrastive learning to improve initial data selection, outperforming existing strategies and random selection across multiple datasets.

Contribution

It introduces a contrastive learning-based method to effectively select initial data in vision active learning, mitigating bias and outliers without requiring annotations.

Findings

Initial query outperforms existing active querying strategies.

Proposed method surpasses random selection by a large margin.

Effective across diverse datasets including medical imaging.

Abstract

Active learning promises to improve annotation efficiency by iteratively selecting the most important data to be annotated first. However, we uncover a striking contradiction to this promise: active learning fails to select data as efficiently as random selection at the first few choices. We identify this as the cold start problem in vision active learning, caused by a biased and outlier initial query. This paper seeks to address the cold start problem by exploiting the three advantages of contrastive learning: (1) no annotation is required; (2) label diversity is ensured by pseudo-labels to mitigate bias; (3) typical data is determined by contrastive features to reduce outliers. Experiments are conducted on CIFAR-10-LT and three medical imaging datasets (i.e. Colon Pathology, Abdominal CT, and Blood Cell Microscope). Our initial query not only significantly outperforms existing active querying strategies but also surpasses random selection by a large margin. We foresee our solution to the cold start problem as a simple yet strong baseline to choose the initial query for vision active learning. Code is available: https://github.com/c-liangyu/CSVAL