逐步探索和利用推理数据以突破细粒度分类壁垒
Progressively Exploring and Exploiting Inference Data to Break Fine-Grained Classification Barrier
AI总结：
本文提出了一种新的学习范式，通过逐步探索和利用推理数据，突破细粒度分类的瓶颈，提升模型对动态语义变化的适应能力。
摘要：
当前细粒度分类研究主要集中在细粒度特征学习上。然而，在现实场景中，细粒度数据标注具有挑战性，且特征和语义高度多样且频繁变化。这些问题在传统实验设置与现实应用之间造成了固有障碍，限制了传统细粒度分类方法的有效性。尽管一些近期研究提供了潜在解决方案，但大多数仍然依赖有限的监督信息，无法提供有效的解决方案。在本文中，基于理论分析，我们提出了一种新的学习范式，以突破细粒度分类的障碍。该范式使模型在推理过程中逐步学习，从而利用推理时的无成本数据更准确地表示细粒度类别并适应动态语义变化。在此基础上，设计了高效的EXPloring和EXPloiting策略和方法（EXP2）。其中，根据类别表示探索有用的推理数据样本，并利用这些样本优化分类器。实验结果展示了我们方法的广泛有效性，为未来深入理解和探索现实中的细粒度分类提供了指导。
英文摘要：
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 at inference time 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
