Semi-Supervised Learning via Triplet Network Based Active Learning (Student Abstract)

Divyanshu Sundriyal, Soumyadeep Ghosh, Mayank Vatsa, Richa Singh

Abstract

This paper presents Triplet AL, a novel active learning framework designed to enhance model performance in data-scarce environments. By leveraging a triplet network to map data into a metric embedding space, the authors introduce the "Top-Two-Margin" metric to identify high-confidence unlabeled samples. These samples are then pseudo-labeled and integrated into the training set. Experimental evaluations on STL-10 and CIFAR-10 benchmarks demonstrate that Triplet AL consistently outperforms traditional active learning baselines across multiple architectures, including LeNet-5, ResNet-152, and DenseNet-121.

Introduction

Deep learning models typically require vast amounts of labeled data to achieve high performance. However, the process of manual labeling is often prohibitively expensive and time-consuming. Active Learning (AL) seeks to mitigate this by strategically selecting the most informative unlabeled samples for labeling.

Traditional AL methods often rely on a classification model’s final softmax output to estimate uncertainty. Unfortunately, softmax scores can be poorly calibrated, leading to unreliable sample selection. This paper proposes a more robust alternative using metric learning, specifically a triplet network, to measure sample confidence more accurately for pseudo-labeling in a semi-supervised setting.

Methodology

The proposed Triplet AL framework utilizes a dual-model architecture consisting of a standard classification model ($M_1$) and a Triplet Network ($M_2$). The Triplet Network is trained using triplet loss to ensure that samples from the same class are clustered together in an embedding space while samples from different classes are pushed apart.

The Top-Two-Margin Metric

To select samples for pseudo-labeling, the system first calculates the mean embedding (class center) for each class using the initial labeled dataset. For any unlabeled sample $u_i$, the triplet network generates an embedding, and the algorithm calculates the distance to the nearest class center ($D_{i1}$) and the second nearest center ($D_{i2}$).

Figure 1: Visualization of the Top-Two-Margin metric calculation in the embedding space.

The confidence metric, or Margin, is defined as: $$\text{Margin} = D_{i2} - D_{i1}$$

Unlike standard active learning which prioritizes the most uncertain samples (smallest margin) for human labeling, Triplet AL selects samples with the largest margin. These high-confidence samples are assigned a pseudo-label based on their nearest center and added to the training set for iterative retraining.

Experimental Results

The researchers evaluated Triplet AL on the STL-10 and CIFAR-10 datasets. The method was tested against several baselines, including Random Sampling, Least Certainty, BALD, and DeepFool AL.

Figure 2: Performance comparison of Triplet AL against standard active learning baselines.

Key findings include:

  • Consistent Superiority: Triplet AL (indicated by the red diamond line in performance plots) consistently outperformed all other methods as more samples were added.
  • Significant Gains in Small Models: The most dramatic improvements were seen in LeNet-5, with an accuracy jump of 14.55% on STL-10 and 6.29% on CIFAR-10.
  • Scalability to Deep Architectures: The method also provided steady gains for ResNet-152 and DenseNet-121, typically ranging from 1.5% to 2.1%.

Discussion and Future Work

The success of Triplet AL suggests that distances in a learned metric space provide a more reliable indicator of class membership than raw classification probabilities. By allowing the model to act as its own "Oracle" through pseudo-labeling high-confidence samples, the training set can grow effectively with minimal human intervention.

However, the authors note that maintaining two separate models increases computational overhead. Future research will focus on multi-task learning to unify classification and embedding into a single model. Additionally, strategies to mitigate "confirmation bias" from potential pseudo-label noise and improving scalability for datasets with a high number of classes remain important areas for exploration.

Summary updated

Abstract

In recent years, deep learning models have pushed state-of-the-art accuracies for several machine learning tasks. However, such models require a large amount of (supervised) data for training. While unlabelled data is available in abundance, manually labeling them is very costly. Active learning techniques helps in utilizing unlabelled data which may result in an improved classification model. In this research, we present an active learning algorithm which can help in increasing performance of deep learning models by using large amount of unlabelled data. A novel active learning algorithm, Triplet AL is proposed which uses a triplet network to select samples from an unlabelled data set. Previous active learning methods rely on classification model's final prediction scores as a measure of confidence for an unlabelled sample. We propose a more reliable confidence measure, termed as Top-Two-Margin which is given by the Triplet Network. The proposed algorithm shows improved performance compared to other active learning approaches.
BibTeX
@inproceedings{sundriyal2021semi,
  author = {Divyanshu Sundriyal and Soumyadeep Ghosh and Mayank Vatsa and Richa Singh},
  title = {{Semi-Supervised Learning via Triplet Network Based Active Learning (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2021},
  doi = {10.1609/aaai.v35i18.17948},
}
Figure