Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects
This is an incremental contribution that provides a systematic summary and taxonomy for researchers in fine-grained ZSL, without introducing new methods or benchmarks.
The paper presents a comprehensive review of fine-grained zero-shot learning (ZSL), addressing problems like seen/unseen domain bias and misaligned visual-semantics mapping, but does not report specific experimental results or numbers.
Recent zero-shot learning (ZSL) approaches have integrated fine-grained analysis, i.e., fine-grained ZSL, to mitigate the commonly known seen/unseen domain bias and misaligned visual-semantics mapping problems, and have made profound progress. Notably, this paradigm differs from existing close-set fine-grained methods and, therefore, can pose unique and nontrivial challenges. However, to the best of our knowledge, there remains a lack of systematic summaries of this topic. To enrich the literature of this domain and provide a sound basis for its future development, in this paper, we present a broad review of recent advances for fine-grained analysis in ZSL. Concretely, we first provide a taxonomy of existing methods and techniques with a thorough analysis of each category. Then, we summarize the benchmark, covering publicly available datasets, models, implementations, and some more details as a library. Last, we sketch out some related applications. In addition, we discuss vital challenges and suggest potential future directions.