Transfer Learning Applied to Computer Vision Problems: Survey on Current Progress, Limitations, and Opportunities
This is an incremental survey that reviews existing progress, limitations, and opportunities in TL for computer vision, aimed at researchers and practitioners in the field.
The paper surveys the application of Transfer Learning (TL) to computer vision problems, highlighting its role in reducing data and computational requirements while achieving comparable accuracy to traditional methods.
The field of Computer Vision (CV) has faced challenges. Initially, it relied on handcrafted features and rule-based algorithms, resulting in limited accuracy. The introduction of machine learning (ML) has brought progress, particularly Transfer Learning (TL), which addresses various CV problems by reusing pre-trained models. TL requires less data and computing while delivering nearly equal accuracy, making it a prominent technique in the CV landscape. Our research focuses on TL development and how CV applications use it to solve real-world problems. We discuss recent developments, limitations, and opportunities.