In computer vision, significant advances have been made on object detection with the rapid
development of deep convolutional neural networks (CNN). This paper provides a …

Small object detection is a challenging problem in computer vision. It has been widely
applied in defense military, transportation, industry, etc. To facilitate in-depth understanding …

Convolutional neural networks (CNNs) have made resounding success in many computer
vision tasks such as image classification and object detection. However, their performance …

Detecting tiny objects is a very challenging problem since a tiny object only contains a few
pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory …

Detecting tiny objects is one of the main obstacles hindering the development of object
detection. The performance of generic object detectors tends to drastically deteriorate on tiny …

Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training
instances, and is useful when manual annotation is time-consuming or data acquisition is …

Current state-of-the-art convolutional architectures for object detection are manually
designed. Here we aim to learn a better architecture of feature pyramid network for object …

Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains
a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny …

Detecting small or tiny objects is always a difficult and challenging issue in computer vision.
In this paper, we provide a latest and comprehensive survey of deep learning-based …

Conventional deep learning based methods for object detection require a large amount of
bounding box annotations for training, which is expensive to obtain such high quality …