PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning

TL;DR

PEPL introduces a semi-supervised learning method that uses refined pseudo-labels based on semantic content to improve fine-grained image classification accuracy.

Contribution

The paper proposes a novel pseudo-labeling approach that leverages Class Activation Maps for semantic refinement, enhancing semi-supervised fine-grained classification.

Findings

Achieves state-of-the-art results on benchmark datasets.

Significantly improves accuracy over existing semi-supervised methods.

Enhances robustness in fine-grained classification tasks.

Abstract

Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annotations remains a major challenge, especially in scenarios where obtaining high-quality labeled data is costly or time-consuming. To address this limitation, we introduce Precision-Enhanced Pseudo-Labeling(PEPL) approach specifically designed for fine-grained image classification within a semi-supervised learning framework. Our method leverages the abundance of unlabeled data by generating high-quality pseudo-labels that are progressively refined through two key phases: initial pseudo-label generation and semantic-mixed pseudo-label generation. These phases utilize Class Activation Maps (CAMs) to accurately estimate the semantic content and generate refined labels that capture the essential details necessary for fine-grained classification. By focusing on semantic-level information, our approach effectively addresses the limitations of standard data augmentation and image-mixing techniques in preserving critical fine-grained features. We achieve state-of-the-art performance on benchmark datasets, demonstrating significant improvements over existing semi-supervised strategies, with notable boosts in accuracy and robustness.