Image Classification with Deep Reinforcement Active Learning

TL;DR

This paper introduces a deep reinforcement learning-based active learning framework for image classification that adaptively selects data samples, reducing labeling effort and outperforming existing strategies across multiple benchmarks.

Contribution

We propose an adaptive active learning method using deep reinforcement learning and DDPG to dynamically optimize sample selection in image classification tasks.

Findings

Outperforms existing active learning strategies on benchmark datasets.

Reduces labeling effort while maintaining high classification accuracy.

Demonstrates adaptability across different datasets and scenarios.

Abstract

Deep learning is currently reaching outstanding performances on different tasks, including image classification, especially when using large neural networks. The success of these models is tributary to the availability of large collections of labeled training data. In many real-world scenarios, labeled data are scarce, and their hand-labeling is time, effort and cost demanding. Active learning is an alternative paradigm that mitigates the effort in hand-labeling data, where only a small fraction is iteratively selected from a large pool of unlabeled data, and annotated by an expert (a.k.a oracle), and eventually used to update the learning models. However, existing active learning solutions are dependent on handcrafted strategies that may fail in highly variable learning environments (datasets, scenarios, etc). In this work, we devise an adaptive active learning method based on Markov Decision Process (MDP). Our framework leverages deep reinforcement learning and active learning together with a Deep Deterministic Policy Gradient (DDPG) in order to dynamically adapt sample selection strategies to the oracle's feedback and the learning environment. Extensive experiments conducted on three different image classification benchmarks show superior performances against several existing active learning strategies.