Search Results for author: Xinjing Cheng

Found 12 papers, 8 papers with code

VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

1 code implementation22 Nov 2022 Mingjia Li, Binhui Xie, Shuang Li, Chi Harold Liu, Xinjing Cheng

However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality.

Domain Adaptation Semantic Segmentation

Active Learning for Domain Adaptation: An Energy-Based Approach

1 code implementation2 Dec 2021 Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, Xinjing Cheng, Guoren Wang

Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains.

Active Learning Unsupervised Domain Adaptation

Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation

1 code implementation11 May 2021 Shuang Li, Binhui Xie, Bin Zang, Chi Harold Liu, Xinjing Cheng, Ruigang Yang, Guoren Wang

Specifically, we first design a pixel-wise contrastive loss by considering the correspondences between semantic distributions and pixel-wise representations from both domains.

Self-Supervised Learning Semantic Segmentation

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

1 code implementation CVPR 2021 Shuang Li, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Feng Qiao, Xinjing Cheng

Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes.

Data Augmentation Meta-Learning

ODE-CNN: Omnidirectional Depth Extension Networks

no code implementations3 Jul 2020 Xinjing Cheng, Peng Wang, Yanqi Zhou, Chenye Guan, Ruigang Yang

Omnidirectional 360{\deg} camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view(FoV).

CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion

no code implementations13 Nov 2019 Xinjing Cheng, Peng Wang, Chenye Guan, Ruigang Yang

In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resources needed at each pixel could be dynamically assigned upon requests.

Depth Completion Stereo-LiDAR Fusion

Part-level Car Parsing and Reconstruction from Single Street View

no code implementations27 Nov 2018 Qichuan Geng, Hong Zhang, Xinyu Huang, Sen Wang, Feixiang Lu, Xinjing Cheng, Zhong Zhou, Ruigang Yang

As it is labor-intensive to annotate semantic parts on real street views, we propose a specific approach to implicitly transfer part features from synthesized images to real street views.

Car Pose Estimation Domain Adaptation +1

Learning Depth with Convolutional Spatial Propagation Network

1 code implementation4 Oct 2018 Xinjing Cheng, Peng Wang, Ruigang Yang

In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for various depth estimation tasks.

Depth Completion Depth Estimation +3

The ApolloScape Open Dataset for Autonomous Driving and its Application

2 code implementations16 Mar 2018 Xinyu Huang, Peng Wang, Xinjing Cheng, Dingfu Zhou, Qichuan Geng, Ruigang Yang

In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving.

Autonomous Driving Instance Segmentation +2

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