Chengjian Feng

I am currently a researcher at Meituan Inc.

Home  /  Email  /  Github  /  Google Scholar

My research interests lie in the areas of computer vision and deep learning. I am particularly interested in object detection, including 2D object detection, 3D object detection (both vision-based and LiDAR-based) and open-vocabulary object detection.

We introduce a novel paradigm to enhance the ability of object detector by training on synthetic dataset generated from diffusion models.

We propose an Azimuth-equivariant Detector (AeDet) that is able to perform azimuth-invariant multi-view 3D object detection.

We propose an open-vocabulary object detector PromptDet, which is able to detect novel categories without any manual annotations.

We propose a Task-aligned One-stage Object Detection (TOOD) that explicitly aligns the classification and localization tasks in a learning-based manner.

We balance the classification of the long-tailed detector via an Equilibrium Loss (EBL) and a Memory-augmented Feature Sampling (MFS) method.

We propose a powerful model for unsupervised domain adaptation by introducing Mean Teacher as a target classifier of SBADA-GAN.

Template gratefully stolen from here.