# Image Classification with Deep Reinforcement Active Learning

arXiv: https://arxiv.org/abs/2412.19877 · HTML: https://mlsanity.com/paper/2412.19877/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 35 of its 119 references that are in the map.
- First posted on arXiv 27 Dec 2024.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Neural Operator: Graph Kernel Network for Partial Differential Equations](https://mlsanity.com/paper/2003.03485/) (2020)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [To understand deep learning we need to understand kernel learning](https://mlsanity.com/paper/1802.01396/) (2018)
- [QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information](https://mlsanity.com/paper/2103.05399/) (2021)
- [Metrics for Multi-Class Classification: an Overview](https://mlsanity.com/paper/2008.05756/) (2020)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [Discriminative Active Learning](https://mlsanity.com/paper/1907.06347/) (2019)
- [Stochastic Variational Deep Kernel Learning](https://mlsanity.com/paper/1611.00336/) (2016)
- [Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification](https://mlsanity.com/paper/1702.05891/) (2017)
- [Multi-label Image Recognition by Recurrently Discovering Attentional Regions](https://mlsanity.com/paper/1711.02816/) (2017)
- [The Promises and Pitfalls of Deep Kernel Learning](https://mlsanity.com/paper/2102.12108/) (2021)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification](https://mlsanity.com/paper/1912.07872/) (2019)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [Multi-Label Classification with Label Graph Superimposing](https://mlsanity.com/paper/1911.09243/) (2019)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition](https://mlsanity.com/paper/1712.07465/) (2017)
- [Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.03328/) (2021)
- [Deep Active Learning with Adaptive Acquisition](https://mlsanity.com/paper/1906.11471/) (2019)
- [GM-MLIC: Graph Matching based Multi-Label Image Classification](https://mlsanity.com/paper/2104.14762/) (2021)

## Abstract (arXiv)

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.