Lung cancer has one of the highest mortalities of all cancers. According to the National Lung
Screening Trial, patients who underwent low-dose computed tomography (CT) scanning …

The complex nature of combining localization and classification in object detection has
resulted in the flourished development of methods. Previous works tried to improve the …

This paper presents a new vision Transformer, called Swin Transformer, that capably serves
as a general-purpose backbone for computer vision. Challenges in adapting Transformer …

Although convolutional neural networks (CNNs) have achieved great success in computer
vision, this work investigates a simpler, convolution-free backbone network useful for many …

Recently, Vision Transformer and its variants have shown great promise on various
computer vision tasks. The ability of capturing short-and long-range visual dependencies …

In this paper, we present a novel Dynamic DETR (Detection with Transformers) approach by
introducing dynamic attentions into both the encoder and decoder stages of DETR to break …

We present DetCo, a simple yet effective self-supervised approach for object detection.
Unsupervised pre-training methods have been recently designed for object detection, but …

We present QueryInst, a new perspective for instance segmentation. QueryInst is a multi-
stage end-to-end system that treats instances of interest as learnable queries, enabling …

Multi-object tracking (MOT) is an important problem in computer vision which has a wide
range of applications. Formulating MOT as multi-task learning of object detection and re-ID …

This work presents a simple vision transformer design as a strong baseline for object
localization and instance segmentation tasks. Transformers recently demonstrate …