Fine-Grained Features in Any-Shot Learning: A Survey

Deep learning has achieved remarkable success across a wide range of domains and applications over the past few decades. However, the high performance of most deep learning models is heavily dependent on large volumes of labeled data, which is often labor-intensive, time-consuming, and sometimes impractical to collect. To address this challenge, anyshot learning (ASL)—such as few-shot and zero-shot learning—has been proposed to recognize novel classes with only a few labeled examples or class descriptions. The human visual system excels at identifying discriminative regions in complex scenes, and inspired by this capability, fine-grained features are extracted from input data to emphasize key regions, advancing the field of ASL. Despite the success of these methods, there is a lack of comprehensive surveys on the use of fine-grained features in ASL. This paper provides a detailed survey of recent research on fine-grained features in few-shot and zero-shot learning, offering summaries of various approaches, discussing their strengths and limitations, and identifying key challenges, future directions, and research opportunities to drive further advancements in the field. We also explore the potential of ASL in semi-supervised learning, weakly supervised learning, and domain adaptation and highlight its application