PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognition

TL;DR

PP-SSL introduces a novel self-supervised learning framework that enhances fine-grained visual recognition by filtering irrelevant features and emphasizing subtle discriminative details, outperforming existing methods.

Contribution

The paper proposes PP-SSL, a new self-supervised learning approach with AIS and IADM components, specifically designed to improve fine-grained recognition by focusing on subtle differences.

Findings

PP-SSL significantly outperforms existing methods on various datasets.

The use of GradCAM from original images reveals more subtle class differences.

Knowledge distillation guides the model to focus on discriminative features.

Abstract

Self-supervised learning is emerging in fine-grained visual recognition with promising results. However, existing self-supervised learning methods are often susceptible to irrelevant patterns in self-supervised tasks and lack the capability to represent the subtle differences inherent in fine-grained visual recognition (FGVR), resulting in generally poorer performance. To address this, we propose a novel Priority-Perception Self-Supervised Learning framework, denoted as PP-SSL, which can effectively filter out irrelevant feature interference and extract more subtle discriminative features throughout the training process. Specifically, it composes of two main parts: the Anti-Interference Strategy (AIS) and the Image-Aided Distinction Module (IADM). In AIS, a fine-grained textual description corpus is established, and a knowledge distillation strategy is devised to guide the model in eliminating irrelevant features while enhancing the learning of more discriminative and high-quality features. IADM reveals that extracting GradCAM from the original image effectively reveals subtle differences between fine-grained categories. Compared to features extracted from intermediate or output layers, the original image retains more detail, allowing for a deeper exploration of the subtle distinctions among fine-grained classes. Extensive experimental results indicate that the PP-SSL significantly outperforms existing methods across various datasets, highlighting its effectiveness in fine-grained recognition tasks. Our code will be made publicly available upon publication.