Search Results for author: Yu Xiang

Found 67 papers, 30 papers with code

HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction

no code implementations10 Jun 2024 Jikai Wang, Qifan Zhang, Yu-Wei Chao, Bowen Wen, Xiaohu Guo, Yu Xiang

We introduce a data capture system and a new dataset named HO-Cap that can be used to study 3D reconstruction and pose tracking of hands and objects in videos.

3D Reconstruction Pose Tracking +1

Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation

1 code implementation28 May 2024 Yangxiao Lu, Jishnu Jaykumar P, Yunhui Guo, Nicholas Ruozzi, Yu Xiang

Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance.

Instance Segmentation Object Proposal Generation +1

Training-Conditional Coverage Bounds under Covariate Shift

no code implementations26 May 2024 Mehrdad Pournaderi, Yu Xiang

Training-conditional coverage guarantees in conformal prediction concern the concentration of the error distribution, conditional on the training data, below some nominal level.

Conformal Prediction

Causal Inference from Slowly Varying Nonstationary Processes

no code implementations11 May 2024 Kang Du, Yu Xiang

Causal inference from observational data following the restricted structural causal models (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or non-linearity.

Causal Identification Causal Inference +1

Mining Invariance from Nonlinear Multi-Environment Data: Binary Classification

no code implementations23 Apr 2024 Austin Goddard, Kang Du, Yu Xiang

Making predictions in an unseen environment given data from multiple training environments is a challenging task.

Binary Classification

Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms

no code implementations21 Apr 2024 Mehrdad Pournaderi, Yu Xiang

The training-conditional coverage performance of the conformal prediction is known to be empirically sound.

Conformal Prediction

Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification

no code implementations17 Apr 2024 Shivvrat Arya, Yu Xiang, Vibhav Gogate

We present a unified framework called deep dependency networks (DDNs) that combines dependency networks and deep learning architectures for multi-label classification, with a particular emphasis on image and video data.

Multi-Label Classification

Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis

no code implementations25 Mar 2024 Jie Qiao, Yu Xiang, Zhengming Chen, Ruichu Cai, Zhifeng Hao

Fortunately, in this work, we found that the causal order from $X$ to its child $Y$ is identifiable if $X$ is a root vertex and has at least two directed paths to $Y$, or the ancestor of $X$ with the most directed path to $X$ has a directed path to $Y$ without passing $X$.

Causal Discovery Epidemiology

Grasping Trajectory Optimization with Point Clouds

no code implementations8 Mar 2024 Yu Xiang, Sai Haneesh Allu, Rohith Peddi, Tyler Summers, Vibhav Gogate

The task space of a robot is represented by a point cloud that can be obtained from depth sensors.

Collision Avoidance Robotic Grasping

RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features

no code implementations4 Mar 2024 Howard H. Qian, Yangxiao Lu, Kejia Ren, Gaotian Wang, Ninad Khargonkar, Yu Xiang, Kaiyu Hang

In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects.

Object Segmentation +2

Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning

1 code implementation10 Feb 2024 Kang Du, Yu Xiang

We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness.

regression Self-Supervised Learning

Incorporating Riemannian Geometric Features for Learning Coefficient of Pressure Distributions on Airplane Wings

no code implementations22 Dec 2023 Liwei Hu, Wenyong Wang, Yu Xiang, Stefan Sommer

The aerodynamic coefficients of aircrafts are significantly impacted by its geometry, especially when the angle of attack (AoA) is large.

Deep Attention

Segment Every Out-of-Distribution Object

1 code implementation CVPR 2024 Wenjie Zhao, Jia Li, Xin Dong, Yu Xiang, Yunhui Guo

Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects.

Object Segmentation +1

AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer

1 code implementation22 Sep 2023 Leixin Yang, Yu Xiang

This method uses the Attention mechanism of Transformer itself to reduce the influence of noises and aberrant values in the original samples on the prediction results, without increasing additional trainable parameters, and the computational cost is very low, thereby avoiding the problem of high resource consumption in common Mixup methods such as Sentence Mixup .

Data Augmentation Sentence +2

Pedestrian Recognition with Radar Data-Enhanced Deep Learning Approach Based on Micro-Doppler Signatures

no code implementations14 Jun 2023 Haoming Li, Yu Xiang, Haodong Xu, Wenyong Wang

As a hot topic in recent years, the ability of pedestrians identification based on radar micro-Doppler signatures is limited by the lack of adequate training data.

Generative Adversarial Network

Structural Hawkes Processes for Learning Causal Structure from Discrete-Time Event Sequences

1 code implementation10 May 2023 Jie Qiao, Ruichu Cai, Siyu Wu, Yu Xiang, Keli Zhang, Zhifeng Hao

Learning causal structure among event types from discrete-time event sequences is a particularly important but challenging task.

Novel deep learning methods for 3D flow field segmentation and classification

no code implementations10 May 2023 Xiaorui Bai, Wenyong Wang, Jun Zhang, Yueqing Wang, Yu Xiang

Flow field segmentation and classification help researchers to understand vortex structure and thus turbulent flow.

Classification Segmentation

Dual Residual Attention Network for Image Denoising

1 code implementation7 May 2023 Wencong Wu, Shijie Liu, Yi Zhou, Yungang Zhang, Yu Xiang

The proposed DRANet includes two different parallel branches, which can capture complementary features to enhance the learning ability of the model.

 Ranked #1 on Image Denoising on SIDD (Average PSNR metric)

Image Denoising

Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction

1 code implementation7 Feb 2023 Yangxiao Lu, Ninad Khargonkar, Zesheng Xu, Charles Averill, Kamalesh Palanisamy, Kaiyu Hang, Yunhui Guo, Nicholas Ruozzi, Yu Xiang

By applying multi-object tracking and video object segmentation on the images collected via robot pushing, our system can generate segmentation masks of all the objects in these images in a self-supervised way.

Multi-Object Tracking Object +6

Deep Dependency Networks for Multi-Label Classification

no code implementations1 Feb 2023 Shivvrat Arya, Yu Xiang, Vibhav Gogate

We propose a simple approach which combines the strengths of probabilistic graphical models and deep learning architectures for solving the multi-label classification task, focusing specifically on image and video data.

Action Classification Classification +2

Generalized Invariant Matching Property via LASSO

no code implementations14 Jan 2023 Kang Du, Yu Xiang

In this work, by formulating a high-dimensional problem with intrinsic sparsity, we generalize the invariant matching property for an important setting when only the target is intervened.

SLGTformer: An Attention-Based Approach to Sign Language Recognition

1 code implementation21 Dec 2022 Neil Song, Yu Xiang

However, this frontal appearance can be quantified as a temporal sequence of human body pose, leading to Sign Language Recognition through the learning of spatiotemporal dynamics of skeleton keypoints.

Sign Language Recognition

On Large-Scale Multiple Testing Over Networks: An Asymptotic Approach

no code implementations29 Nov 2022 Mehrdad Pournaderi, Yu Xiang

We take an asymptotic approach and propose two methods, proportion-matching and greedy aggregation, tailored to distributed settings.

Sample-and-Forward: Communication-Efficient Control of the False Discovery Rate in Networks

no code implementations5 Oct 2022 Mehrdad Pournaderi, Yu Xiang

This work concerns controlling the false discovery rate (FDR) in networks under communication constraints.

Learning Invariant Representations under General Interventions on the Response

no code implementations22 Aug 2022 Kang Du, Yu Xiang

One principled approach is to adopt the structural causal models to describe training and test models, following the invariance principle which says that the conditional distribution of the response given its predictors remains the same across environments.

Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network

no code implementations30 Jul 2022 Zhen Xing, Yijiang Chen, Zhixin Ling, Xiangdong Zhou, Yu Xiang

In this paper, we present a Memory Prior Contrastive Network (MPCN) that can store shape prior knowledge in a few-shot learning based 3D reconstruction framework.

3D Reconstruction Contrastive Learning +3

FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments

3 code implementations6 Jul 2022 Jishnu Jaykumar P, Yu-Wei Chao, Yu Xiang

We introduce the Few-Shot Object Learning (FewSOL) dataset for object recognition with a few images per object.

Attribute Classification +6

A Manifold-based Airfoil Geometric-feature Extraction and Discrepant Data Fusion Learning Method

no code implementations23 Jun 2022 Yu Xiang, Guangbo Zhang, Liwei Hu, Jun Zhang, Wenyong Wang

Geometrical shape of airfoils, together with the corresponding flight conditions, are crucial factors for aerodynamic performances prediction.

Multi-Task Learning

An Invariant Matching Property for Distribution Generalization under Intervened Response

no code implementations18 May 2022 Kang Du, Yu Xiang

The task of distribution generalization concerns making reliable prediction of a response in unseen environments.

A Multi-Characteristic Learning Method with Micro-Doppler Signatures for Pedestrian Identification

no code implementations23 Mar 2022 Yu Xiang, Yu Huang, Haodong Xu, Guangbo Zhang, Wenyong Wang

The identification of pedestrians using radar micro-Doppler signatures has become a hot topic in recent years.

Variable Selection with the Knockoffs: Composite Null Hypotheses

no code implementations6 Mar 2022 Mehrdad Pournaderi, Yu Xiang

The fixed-X knockoff filter is a flexible framework for variable selection with false discovery rate (FDR) control in linear models with arbitrary design matrices (of full column rank) and it allows for finite-sample selective inference via the Lasso estimates.

Variable Selection

iCaps: Iterative Category-level Object Pose and Shape Estimation

1 code implementation31 Dec 2021 Xinke Deng, Junyi Geng, Timothy Bretl, Yu Xiang, Dieter Fox

The auto-encoder can be used in a particle filter framework to estimate and track 6D poses of objects in a category.


Differentially Private Variable Selection via the Knockoff Filter

no code implementations12 Sep 2021 Mehrdad Pournaderi, Yu Xiang

The knockoff filter, recently developed by Barber and Candes, is an effective procedure to perform variable selection with a controlled false discovery rate (FDR).

Variable Selection

A Subsampling-Based Method for Causal Discovery on Discrete Data

no code implementations31 Aug 2021 Austin Goddard, Yu Xiang

Inferring causal directions on discrete and categorical data is an important yet challenging problem.

Causal Discovery

RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks

1 code implementation29 Jun 2021 Christopher Xie, Arsalan Mousavian, Yu Xiang, Dieter Fox

We postulate that a network architecture that encodes relations between objects at a high-level can be beneficial.

Graph Neural Network

RGB-D Local Implicit Function for Depth Completion of Transparent Objects

1 code implementation CVPR 2021 Luyang Zhu, Arsalan Mousavian, Yu Xiang, Hammad Mazhar, Jozef van Eenbergen, Shoubhik Debnath, Dieter Fox

Key to our approach is a local implicit neural representation built on ray-voxel pairs that allows our method to generalize to unseen objects and achieve fast inference speed.

Depth Completion Depth Estimation +1

Deterministic distribution of multipartite entanglement and steering in a quantum network by separable states

no code implementations5 Jan 2021 Meihong Wang, Yu Xiang, Haijun Kang, Dongmei Han, Yang Liu, Qiongyi He, Qihuang Gong, Xiaolong Su, Kunchi Peng

We experimentally demonstrate the deterministic distribution of two- and three-mode Gaussian entanglement and steering by transmitting separable states in a network consisting of a quantum server and multiple users.

Quantum Physics

Causal Inference from Slowly Varying Nonstationary Processes

no code implementations23 Dec 2020 Kang Du, Yu Xiang

Causal inference from observational data following the restricted structural causal model (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or nonlinearity.

Causal Discovery Causal Identification +3

Aerodynamic Data Predictions Based on Multi-task Learning

no code implementations15 Oct 2020 Liwei Hu, Yu Xiang, Jun Zhan, Zifang Shi, Wenzheng Wang

Predicting high-speed data is more difficult than predicting low-speed data, owing to that the number of high-speed data is limited, i. e. the quality of the Burgers' dataset is not satisfactory.

Multi-Task Learning

Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds

1 code implementation2 Oct 2020 Lirui Wang, Yu Xiang, Wei Yang, Arsalan Mousavian, Dieter Fox

We demonstrate that our learned policy can be integrated into a tabletop 6D grasping system and a human-robot handover system to improve the grasping performance of unseen objects.

Imitation Learning Motion Planning +2

Information Laundering for Model Privacy

no code implementations ICLR 2021 Xinran Wang, Yu Xiang, Jun Gao, Jie Ding

In this work, we propose information laundering, a novel framework for enhancing model privacy.

Flow Field Reconstructions with GANs based on Radial Basis Functions

no code implementations11 Aug 2020 Liwei Hu, Wenyong Wang, Yu Xiang, Jun Zhang

Motivated by the problems of existing approaches and inspired by the success of the generative adversarial networks (GANs) in the field of computer vision, we prove an optimal discriminator theorem that the optimal discriminator of a GAN is a radial basis function neural network (RBFNN) while dealing with nonlinear sparse FFD regression and generation.


Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation

1 code implementation30 Jul 2020 Yu Xiang, Christopher Xie, Arsalan Mousavian, Dieter Fox

In this work, we propose a new method for unseen object instance segmentation by learning RGB-D feature embeddings from synthetic data.

Clustering Metric Learning +4

Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection

1 code implementation22 Nov 2019 Lirui Wang, Yu Xiang, Dieter Fox

In robot manipulation, planning the motion of a robot manipulator to grasp an object is a fundamental problem.


Self-supervised 6D Object Pose Estimation for Robot Manipulation

3 code implementations23 Sep 2019 Xinke Deng, Yu Xiang, Arsalan Mousavian, Clemens Eppner, Timothy Bretl, Dieter Fox

In this way, our system is able to continuously collect data and improve its pose estimation modules.


The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation

no code implementations30 Jul 2019 Christopher Xie, Yu Xiang, Arsalan Mousavian, Dieter Fox

We show that our method, trained on this dataset, can produce sharp and accurate masks, outperforming state-of-the-art methods on unseen object instance segmentation.

Object Segmentation +2

PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

1 code implementation22 May 2019 Xinke Deng, Arsalan Mousavian, Yu Xiang, Fei Xia, Timothy Bretl, Dieter Fox

In this work, we formulate the 6D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3D rotation and the 3D translation of an object are decoupled.

6D Pose Estimation 6D Pose Estimation using RGB +3

Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects

8 code implementations27 Sep 2018 Jonathan Tremblay, Thang To, Balakumar Sundaralingam, Yu Xiang, Dieter Fox, Stan Birchfield

Using synthetic data generated in this manner, we introduce a one-shot deep neural network that is able to perform competitively against a state-of-the-art network trained on a combination of real and synthetic data.


DeepIM: Deep Iterative Matching for 6D Pose Estimation

2 code implementations ECCV 2018 Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox

Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality.

6D Pose Estimation 6D Pose Estimation using RGB +1

Recurrent Autoregressive Networks for Online Multi-Object Tracking

no code implementations7 Nov 2017 Kuan Fang, Yu Xiang, Xiaocheng Li, Silvio Savarese

The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detections by processing the external memory.

Multi-Object Tracking Object +1

PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

11 code implementations1 Nov 2017 Yu Xiang, Tanner Schmidt, Venkatraman Narayanan, Dieter Fox

We conduct extensive experiments on our YCB-Video dataset and the OccludedLINEMOD dataset to show that PoseCNN is highly robust to occlusions, can handle symmetric objects, and provide accurate pose estimation using only color images as input.

6D Pose Estimation 6D Pose Estimation using RGB +2

DA-RNN: Semantic Mapping with Data Associated Recurrent Neural Networks

1 code implementation9 Mar 2017 Yu Xiang, Dieter Fox

3D scene understanding is important for robots to interact with the 3D world in a meaningful way.

Scene Understanding

Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

1 code implementation16 Apr 2016 Yu Xiang, Wongun Choi, Yuanqing Lin, Silvio Savarese

In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation.

General Classification Object +4

Learning to Track: Online Multi-Object Tracking by Decision Making

no code implementations ICCV 2015 Yu Xiang, Alexandre Alahi, Silvio Savarese

Online Multi-Object Tracking (MOT) has wide applications in time-critical video analysis scenarios, such as robot navigation and autonomous driving.

Autonomous Driving Decision Making +5

Deep Metric Learning via Lifted Structured Feature Embedding

3 code implementations CVPR 2016 Hyun Oh Song, Yu Xiang, Stefanie Jegelka, Silvio Savarese

Additionally, we collected Online Products dataset: 120k images of 23k classes of online products for metric learning.

Metric Learning Structured Prediction

Data-Driven 3D Voxel Patterns for Object Category Recognition

no code implementations CVPR 2015 Yu Xiang, Wongun Choi, Yuanqing Lin, Silvio Savarese

Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image.

Object Object Recognition +1

A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition

no code implementations CVPR 2015 Roozbeh Mottaghi, Yu Xiang, Silvio Savarese

Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters.

3D Pose Estimation Object +2

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