Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending
and drawing extensive attention both from industry and academia. Conventional …

With the rapid development of deep learning techniques, deep convolutional neural
networks (DCNNs) have become more important for object detection. Compared with …

One-stage object detection is commonly implemented by optimizing two sub-tasks: object
classification and localization, using heads with two parallel branches, which might lead to a …

Transformer, an attention-based encoder–decoder model, has already revolutionized the
field of natural language processing (NLP). Inspired by such significant achievements, some …

One-to-one label assignment in object detection has successfully obviated the need of non-
maximum suppression (NMS) as a postprocessing and makes the pipeline end-to-end …

This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out
that the success of FPN is due to its divide-and-conquer solution to the optimization problem …

Recent advances in label assignment in object detection mainly seek to independently
define positive/negative training samples for each ground-truth (gt) object. In this paper, we …

Accurately ranking the vast number of candidate detections is crucial for dense object
detectors to achieve high performance. Prior work uses the classification score or a …

In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary
orientations having the cluttered surroundings. Unlike the mainstreamed approaches …

The development of detection methods for oriented object detection remains a challenging
task. A considerable obstacle is the wide variation in the shape (eg, aspect ratio) of objects …