Search Results for author: Chengjian Feng

Found 6 papers, 5 papers with code

AeDet: Azimuth-invariant Multi-view 3D Object Detection

1 code implementation CVPR 2023 Chengjian Feng, Zequn Jie, Yujie Zhong, Xiangxiang Chu, Lin Ma

However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization.

3D Object Detection Depth Estimation +2

PromptDet: Towards Open-vocabulary Detection using Uncurated Images

2 code implementations30 Mar 2022 Chengjian Feng, Yujie Zhong, Zequn Jie, Xiangxiang Chu, Haibing Ren, Xiaolin Wei, Weidi Xie, Lin Ma

The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations.

Language Modelling

TOOD: Task-aligned One-stage Object Detection

5 code implementations ICCV 2021 Chengjian Feng, Yujie Zhong, Yu Gao, Matthew R. Scott, Weilin Huang

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 certain level of spatial misalignment in predictions between the two tasks.

object-detection Object Detection

Exploring Classification Equilibrium in Long-Tailed Object Detection

1 code implementation ICCV 2021 Chengjian Feng, Yujie Zhong, Weilin Huang

Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes.

Classification imbalanced classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.