Progressively Exploring and Exploiting Cost-Free Data to Break Fine-Grained Classification Barriers
This addresses the challenge of fine-grained classification for applications with limited supervised data, though it appears incremental as it builds on existing methods.
The paper tackles the problem of fine-grained classification in real-world scenarios where data annotation is difficult and semantics are dynamic, proposing a novel learning paradigm that progressively learns during inference using cost-free data to improve accuracy and adaptability.
Current fine-grained classification research primarily focuses on fine-grained feature learning. However, in real-world scenarios, fine-grained data annotation is challenging, and the features and semantics are highly diverse and frequently changing. These issues create inherent barriers between traditional experimental settings and real-world applications, limiting the effectiveness of conventional fine-grained classification methods. Although some recent studies have provided potential solutions to these issues, most of them still rely on limited supervised information and thus fail to offer effective solutions. In this paper, based on theoretical analysis, we propose a novel learning paradigm to break the barriers in fine-grained classification. This paradigm enables the model to progressively learn during inference, thereby leveraging cost-free data to more accurately represent fine-grained categories and adapt to dynamic semantic changes. On this basis, an efficient EXPloring and EXPloiting strategy and method (EXP2) is designed. Thereinto, useful inference data samples are explored according to class representations and exploited to optimize classifiers. Experimental results demonstrate the general effectiveness of our method, providing guidance for future in-depth understanding and exploration of real-world fine-grained classification.