YOLO has become a central real-time object detection system for robotics, driverless cars,
and video monitoring applications. We present a comprehensive analysis of YOLO's …

Detecting objects remains one of computer vision and image understanding applications'
most fundamental and challenging aspects. Significant advances in object detection have …

In this paper, we provide the observation that too few queries assigned as positive samples
in DETR with one-to-one set matching leads to sparse supervision on the encoder's output …

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 …

The recently-developed DETR approach applies the transformer encoder and decoder
architecture to object detection and achieves promising performance. In this paper, we …

In this report, we present some experienced improvements to YOLO series, forming a new
high-performance detector--YOLOX. We switch the YOLO detector to an anchor-free manner …

Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most
commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss …

In this paper, we present a new tracking architecture with an encoder-decoder transformer
as the key component. The encoder models the global spatio-temporal feature …

We show that the YOLOv4 object detection neural network based on the CSP approach,
scales both up and down and is applicable to small and large networks while maintaining …

DETR has been recently proposed to eliminate the need for many hand-designed
components in object detection while demonstrating good performance. However, it suffers …