315 citations · 862 across the 20 of their papers we have counts for
20 papers
Causal Learning for Heterogeneous Subgroups Based on Nonlinear Causal Kernel Clustering
Lu Liu, Yang Tang, Kexuan Zhang +1
Due to the challenge posed by multi-source and heterogeneous data collected from diverse environments, causal relationships among features can exhibit variations influenced by diff…
Computer vision tasks for intelligent aerospace missions: An overview
Huilin Chen, Qiyu Sun, Fangfei Li +1
Computer vision tasks are crucial for aerospace missions as they help spacecraft to understand and interpret the space environment, such as estimating position and orientation, rec…
GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes
Chaoqiang Zhao, Matteo Poggi, Fabio Tosi +4
This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning proce…
IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation
Qiyu Sun, Huilin Chen, Meng Zheng +3
Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data. Despite the pr…
Causal reasoning in typical computer vision tasks
Kexuan Zhang, Qiyu Sun, Chaoqiang Zhao +1
Deep learning has revolutionized the field of artificial intelligence. Based on the statistical correlations uncovered by deep learning-based methods, computer vision has contribut…
CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation
Ruihao Xia, Chaoqiang Zhao, Meng Zheng +3
Most nighttime semantic segmentation studies are based on domain adaptation approaches and image input. However, limited by the low dynamic range of conventional cameras, images fa…
Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
Qiyu Sun, Pavlo Melnyk, Michael Felsberg +1
Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available.…
RoMa: Robust Dense Feature Matching
Johan Edstedt, Qiyu Sun, Georg Bökman +2
Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences…
Molecular Joint Representation Learning via Multi-modal Information
Tianyu Wu, Yang Tang, Qiyu Sun +1
In recent years, artificial intelligence has played an important role on accelerating the whole process of drug discovery. Various of molecular representation schemes of different…
Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning
Wenqi Ren, Qiyu Sun, Chaoqiang Zhao +1
Learning-based image dehazing methods are essential to assist autonomous systems in enhancing reliability. Due to the domain gap between synthetic and real domains, the internal in…
Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview
Wenqi Ren, Yang Tang, Qiyu Sun +2
Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block, and it plays a cr…
Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learning
Qiyu Sun, Jinbao Fang, Wei Xing Zheng +1
The ability to perform aggressive movements, which are called aggressive flights, is important for quadrotors during navigation. However, aggressive quadrotor flights are still a g…
Learn to Adapt for Monocular Depth Estimation
Qiyu Sun, Gary G. Yen, Yang Tang +1
Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress in virtue of deep learning. However, the performance of…
Unsupervised Monocular Depth Estimation in Highly Complex Environments
Chaoqiang Zhao, Yang Tang, Qiyu Sun
With the development of computational intelligence algorithms, unsupervised monocular depth and pose estimation framework, which is driven by warped photometric consistency, has sh…
Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency
Chongzhen Zhang, Yang Tang, Chaoqiang Zhao +3
Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several works are…
Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
Chaoqiang Zhao, Gary G. Yen, Qiyu Sun +2
Previous work has shown that adversarial learning can be used for unsupervised monocular depth and visual odometry (VO) estimation, in which the adversarial loss and the geometric…
When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
Chongzhen Zhang, Jianrui Wang, Gary G. Yen +5
With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making and control for autonomous systems have improved si…
Monocular Depth Estimation Based On Deep Learning: An Overview
Chaoqiang Zhao, Qiyu Sun, Chongzhen Zhang +2
Depth information is important for autonomous systems to perceive environments and estimate their own state. Traditional depth estimation methods, like structure from motion and st…
Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Yang Tang, Chaoqiang Zhao, Jianrui Wang +6
Autonomous systems possess the features of inferring their own state, understanding their surroundings, and performing autonomous navigation. With the applications of learning syst…
Deep Direct Visual Odometry
Chaoqiang Zhao, Yang Tang, Qiyu Sun +1
Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However,…