Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art

Transformers have rapidly gained popularity in computer vision, especially in the field of object detection. Upon examining the outcomes of state-of-the-art object detection methods, we noticed that transformers consistently outperformed well-established CNN-based detectors in almost every video or image dataset. Small objects have been identified as one of the most challenging object types in detection frameworks due to their low visibility. This article aims to explore the performance benefits offered by such extensive networks and identify potential reasons for their Small Object Detection (SOD) superiority. We aim to investigate potential strategies that could further enhance transformers’ performance in SOD. This survey presents a taxonomy of over 60 research studies on developed transformers for the task of SOD, spanning the years 2020 to 2023. These studies encompass a variety of detection applications, including SOD in generic images, aerial images, medical images, active millimeter images, underwater images, and videos. We also compile and present a list of 12 large-scale datasets suitable for SOD that were overlooked in previous studies and compare the performance of the reviewed studies using popular metrics such as mean Average Precision (mAP), Frames Per Second (FPS), and number of parameters. Researchers can keep track of newer studies on our web page, which is available at: https://github.com/arekavandi/Transformer-SOD.