English
Related papers

Related papers: A Compacted Structure for Cross-domain learning on…

200 papers

Multi-task dense prediction, which aims to jointly solve tasks like semantic segmentation and depth estimation, is crucial for robotics applications but suffers from domain shift when deploying models in new environments. While unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Beomseok Kang , Niluthpol Chowdhury Mithun , Mikhail Sizintsev , Han-Pang Chiu , Supun Samarasekera

Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consistency is usually violated in the dynamic areas, leading to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-19 Rui Li , Dong Gong , Wei Yin , Hao Chen , Yu Zhu , Kaixuan Wang , Xiaozhi Chen , Jinqiu Sun , Yanning Zhang

This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xiaoye Wang , Chen Tang , Xiangyu Yue , Wei-Hong Li

Monocular cameras are attractive for robotic perception due to their low cost and ease of deployment, yet achieving reliable real-time spatial understanding from a single image stream remains challenging. While recent multi-task dense…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 U. V. B. L. Udugama , George Vosselman , Francesco Nex

Lifelong deep learning (LDL) trains neural networks to learn sequentially across tasks while preserving prior knowledge. We propose Task-Aware Multi-Expert (TAME), a continual learning algorithm that leverages task similarity to guide…

Machine Learning · Computer Science 2025-12-15 Jianyu Wang , Jacob Nean-Hua Sheikh , Cat P. Le , Hoda Bidkhori

Photonic neural networks are brain-inspired information processing technology using photons instead of electrons to perform artificial intelligence (AI) tasks. However, existing architectures are designed for a single task but fail to…

Machine Learning · Computer Science 2022-12-02 Zhengyang Duan , Hang Chen , Xing Lin

We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…

Computer Vision and Pattern Recognition · Computer Science 2020-02-28 Shihao Jiang , Dylan Campbell , Miaomiao Liu , Stephen Gould , Richard Hartley

This paper presents Edge-based Mixture of Experts (MoE) Collaborative Computing (EMC2), an optimal computing system designed for autonomous vehicles (AVs) that simultaneously achieves low-latency and high-accuracy 3D object detection.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Linshen Liu , Boyan Su , Junyue Jiang , Guanlin Wu , Cong Guo , Ceyu Xu , Hao Frank Yang

The generalization and performance of stereo matching networks are limited due to the domain gap of the existing synthetic datasets and the sparseness of GT labels in the real datasets. In contrast, monocular depth estimation has achieved…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Yuran Wang , Yingping Liang , Hesong Li , Ying Fu

Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…

Computer Vision and Pattern Recognition · Computer Science 2023-12-20 Jiquan Zhong , Xiaolin Huang , Xiao Yu

Accurately perceiving location and scene is crucial for autonomous driving and mobile robots. Recent advances in deep learning have made it possible to learn egomotion and depth from monocular images in a self-supervised manner, without…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Hao Qu , Lilian Zhang , Xiaoping Hu , Xiaofeng He , Xianfei Pan , Changhao Chen

Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Andrii Litvynchuk , Ivan Livinsky , Anand Ravi , Nima Kalantari , Andrii Tsarov

We introduce MultiDepth, a novel training strategy and convolutional neural network (CNN) architecture that allows approaching single-image depth estimation (SIDE) as a multi-task problem. SIDE is an important part of road scene…

Computer Vision and Pattern Recognition · Computer Science 2019-07-26 Lukas Liebel , Marco Körner

Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Haoqian Liang , Zhichao Li , Ya Yang , Naiyan Wang

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Ziyue Feng , Liang Yang , Longlong Jing , Haiyan Wang , YingLi Tian , Bing Li

This paper addresses the problem of cooperative target tracking using a heterogeneous multi-robot system, where the robots are communicating over a dynamic communication network, and heterogeneity is in terms of different types of sensors…

Robotics · Computer Science 2022-09-23 Shubhankar Gupta , Suresh Sundaram

Deep learning has emerged as a technique of choice for rapid feature extraction across imaging disciplines, allowing rapid conversion of the data streams to spatial or spatiotemporal arrays of features of interest. However, applications of…

Data Analysis, Statistics and Probability · Physics 2021-01-25 Ayana Ghosh , Bobby G. Sumpter , Ondrej Dyck , Sergei V. Kalinin , Maxim Ziatdinov

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our approach is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such redundancy implicitly provides various…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Fangqiang Ding , Andras Palffy , Dariu M. Gavrila , Chris Xiaoxuan Lu

Recently, there have been significant advances in neural methods for tackling knowledge-intensive tasks such as open domain question answering (QA). These advances are fueled by combining large pre-trained language models with learnable…

Computation and Language · Computer Science 2021-04-21 Hengxin Fun , Sunil Gandhi , Sujith Ravi

Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called…

Machine Learning · Computer Science 2018-05-22 Yu Zhang , Ying Wei , Qiang Yang