Curriculum-Based Meta-Pseudo-Labeling on 2D Projections for Active Semi-Supervised Learning

• David Aparco-Cardenas UNICAMP
• Jancarlo F. Gomes UNICAMP
• Alexandre X. Falcão UNICAMP
• Pedro J. de Rezende UNICAMP

Resumo

Semi-supervised learning (SSL) is an effective approach to addressing the scarcity of accurately labeled data, leveraging both labeled and unlabeled samples for deep model training. However, limited labeled data can constrain its effectiveness. Active learning (AL) mitigates this by selecting informative samples for human annotation, enhancing SSL performance. Most state-of-the-art AL and SSL methods depend on pre-trained features and large validation sets for learning representations in classification tasks. We introduce contrastive active Deep Feature Annotation (ca-DeepFA), a method that integrates contrastive learning, active learning, and curriculum-based meta-pseudolabeling to train non-pre-trained CNNs for image classification with minimal labeled data and abundant unlabeled samples. The process begins with unsupervised contrastive pre-training on a small labeled set. At regular epoch intervals, label propagation is applied to 2D deep feature projections. Following this, pseudolabels are selected under a curriculum-driven policy, while an oracle annotates the most informative samples. These contribute to a composite loss function that combines supervised contrastive, supervised, and semi-supervised components-leading to enhanced feature representations for image classification. Evaluated on three real-world biological image datasets with a limited amount of labeled data, our method consistently outperforms baselines and state-of-the-art approaches by improving generalization and reducing annotation effort.

Palavras-chave: Training, Graphics, Annotations, Scalability, Active learning, Contrastive learning, Semisupervised learning, Streaming media, Biology, Image classification