Abstract
Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data, but may generate ambiguous and non-distinguishable representations when lacking adequate labeled samples. With human-in-the-loop, active learning can iteratively select informative unlabeled samples for labeling and training to improve the performance in the SSL framework. However, most existing active learning approaches rely on pre-trained features, which is not suitable for end-to-end learning. To deal with the drawbacks of SSL, in this paper, we propose a novel end-to-end representation learning method, namely ActiveMatch, which combines SSL with contrastive learning and active learning to fully leverage the limited labels. Starting from a small amount of labeled data with unsupervised contrastive learning as a warm-up, ActiveMatch then combines SSL and supervised contrastive learning, and actively selects the most representative samples for labeling during the training, resulting in better representations towards the classification. Compared with MixMatch and FixMatch with the same amount of labeled data, we show that ActiveMatch achieves the state-of-the-art performance, with 89.24% accuracy on CIFAR-10 with 100 collected labels, and 92.20% accuracy with 200 collected labels.
Introduction
Deep learning typically requires massive amounts of labeled data, which is expensive and time-consuming to produce. Semi-supervised learning (SSL) attempts to solve this by using a small labeled set alongside a large unlabeled set. However, if the initial labeled set is too small or poorly chosen, the model may learn "ambiguous" representations that fail to distinguish between classes effectively. While Active Learning (AL) can help by letting the model "ask" for labels on the most informative samples, most existing AL methods rely on pre-trained features and aren't designed for end-to-end training. ActiveMatch bridges this gap, creating a unified system where representation learning and sample selection happen simultaneously.
Methods
ActiveMatch is built upon the FixMatch architecture but introduces several key innovations to create a more robust learning loop:
- Warm-up Phase: The process begins with a "warm-up" using unsupervised contrastive learning. This ensures the encoder produces meaningful initial features before any active sampling occurs.
- Supervised Contrastive Learning ($L^{cl}_S$): Once labels are available, the model uses them to minimize the distance between representations of the same class while repelling different classes, creating tighter, more discriminative clusters.
- Active Sampling Loop: Periodically, the model evaluates the unlabeled set using margin sampling. It identifies samples where the model is most "uncertain"—specifically, those with the smallest difference between the top two predicted class probabilities—and sends them to a human "oracle" for labeling.
- End-to-End Integration: These components are tied together in a single loss function that balances supervised cross-entropy, supervised/unsupervised contrastive losses, and SSL pseudo-labeling.
Results
The authors evaluated ActiveMatch on three standard computer vision benchmarks: CIFAR-10, CIFAR-100, and SVHN. ActiveMatch consistently outperformed SOTA baselines like MixMatch and FixMatch, particularly on more complex datasets.
Key insights from the evaluation include:
- The Power of Uncertainty: By picking samples on the decision boundary (high uncertainty), the model receives a much stronger training signal than it would from random samples.
- CIFAR-10 Performance: ActiveMatch achieved 89.24% accuracy with only 100 labels, compared to FixMatch's 88.99%. With 200 labels, it reached 92.20%.
- CIFAR-100 Performance: The gap was even wider. With 1000 labels, ActiveMatch hit 52.20% accuracy, significantly outperforming FixMatch (47.64%) and MixMatch (32.64%).
- Qualitative Improvement: t-SNE visualizations confirm that ActiveMatch produces cleaner, more distinct class clusters compared to standard SSL approaches.
Conclusion
ActiveMatch demonstrates that integrating active learning and contrastive techniques into an end-to-end SSL framework significantly improves performance with minimal human labeling. While performance on simpler datasets like SVHN is comparable to existing methods, the gains on more complex tasks are substantial. Future work will explore more sophisticated active learning strategies and testing on larger-scale datasets like ImageNet.
Summary updated