Minimax Active Learning
arXiv:2012.10467
Abstract
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. While uncertainty-based strategies are susceptible to outliers, solely relying on sample diversity does not capture the information available on the main task. In this work, we develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner. Our model consists of an entropy minimizing feature encoding network followed by an entropy maximizing classification layer. This minimax formulation reduces the distribution gap between the labeled/unlabeled data, while a discriminator is simultaneously trained to distinguish the labeled/unlabeled data. The highest entropy samples from the classifier that the discriminator predicts as unlabeled are selected for labeling. We evaluate our method on various image classification and semantic segmentation benchmark datasets and show superior performance over the state-of-the-art methods.
Project page is available at https://people.eecs.berkeley.edu/~sayna/mal.html
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Prototypical Networks for Few-shot Learning
- Cost-Effective Active Learning for Deep Image Classification
- Deep Bayesian Active Learning with Image Data
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Generative Adversarial Active Learning
- Cost-Effective Active Learning for Melanoma Segmentation
- Reinforced active learning for image segmentation
- Bayesian Generative Active Deep Learning
- MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation