1 code implementation • 28 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.
no code implementations • 26 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.
no code implementations • 11 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.
no code implementations • 23 Apr 2024 • Austin Goddard, Kang Du, Yu Xiang
Making predictions in an unseen environment given data from multiple training environments is a challenging task.
no code implementations • 21 Apr 2024 • Mehrdad Pournaderi, Yu Xiang
The training-conditional coverage performance of the conformal prediction is known to be empirically sound.
no code implementations • 17 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.
no code implementations • 25 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 $X$.
no code implementations • 8 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.
no code implementations • 4 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.
1 code implementation • 10 Feb 2024 • Kang Du, Yu Xiang
We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness.
no code implementations • 22 Dec 2023 • Rohith Peddi, Shivvrat Arya, Bharath Challa, Likhitha Pallapothula, Akshay Vyas, Jikai Wang, Qifan Zhang, Vasundhara Komaragiri, Eric Ragan, Nicholas Ruozzi, Yu Xiang, Vibhav Gogate
Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives.
no code implementations • 22 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.
1 code implementation • 27 Nov 2023 • 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.
1 code implementation • 22 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 .
1 code implementation • 6 Jul 2023 • Jishnu Jaykumar P, Kamalesh Palanisamy, Yu-Wei Chao, Xinya Du, Yu Xiang
The two encoders are used to compute prototypes of image classes for classification.
1 code implementation • 27 Jun 2023 • Ninad Khargonkar, Sai Haneesh Allu, Yangxiao Lu, Jishnu Jaykumar P, Balakrishnan Prabhakaran, Yu Xiang
We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on pick-and-place.
no code implementations • 14 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.
no code implementations • 10 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.
1 code implementation • 10 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.
1 code implementation • 7 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)
1 code implementation • 7 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.
no code implementations • 1 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.
no code implementations • 14 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.
1 code implementation • 21 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.
no code implementations • 29 Nov 2022 • Mehrdad Pournaderi, Yu Xiang
We take an asymptotic approach and propose two methods, proportion-matching and greedy aggregation, tailored to distributed settings.
1 code implementation • 21 Nov 2022 • Yangxiao Lu, Yuqiao Chen, Nicholas Ruozzi, Yu Xiang
To illustrate the effectiveness of our method, we apply MSMFormer to unseen object instance segmentation.
Ranked #1 on Unseen Object Instance Segmentation on OCID
no code implementations • 5 Oct 2022 • Mehrdad Pournaderi, Yu Xiang
This work concerns controlling the false discovery rate (FDR) in networks under communication constraints.
no code implementations • 22 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.
no code implementations • 30 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.
3 code implementations • 6 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.
no code implementations • 23 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.
no code implementations • 19 May 2022 • Yu-Wei Chao, Chris Paxton, Yu Xiang, Wei Yang, Balakumar Sundaralingam, Tao Chen, Adithyavairavan Murali, Maya Cakmak, Dieter Fox
We analyze the performance of a set of baselines and show a correlation with a real-world evaluation.
no code implementations • 18 May 2022 • Kang Du, Yu Xiang
The task of distribution generalization concerns making reliable prediction of a response in unseen environments.
no code implementations • 23 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.
no code implementations • 6 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.
1 code implementation • 31 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.
1 code implementation • 30 Nov 2021 • Suraj Kothawade, Saikat Ghosh, Sumit Shekhar, Yu Xiang, Rishabh Iyer
We propose TALISMAN, a novel framework for Targeted Active Learning or object detectIon with rare slices using Submodular MutuAl iNformation.
no code implementations • 12 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).
no code implementations • 31 Aug 2021 • Austin Goddard, Yu Xiang
Inferring causal directions on discrete and categorical data is an important yet challenging problem.
1 code implementation • 29 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.
2 code implementations • CVPR 2021 • Yu-Wei Chao, Wei Yang, Yu Xiang, Pavlo Molchanov, Ankur Handa, Jonathan Tremblay, Yashraj S. Narang, Karl Van Wyk, Umar Iqbal, Stan Birchfield, Jan Kautz, Dieter Fox
We introduce DexYCB, a new dataset for capturing hand grasping of 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.
no code implementations • 5 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
no code implementations • 23 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.
no code implementations • 15 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.
1 code implementation • 2 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.
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.
no code implementations • 11 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.
1 code implementation • 30 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.
1 code implementation • 16 Jul 2020 • Christopher Xie, Yu Xiang, Arsalan Mousavian, Dieter Fox
We also show that our method can segment unseen objects for robot grasping.
1 code implementation • CVPR 2020 • Keunhong Park, Arsalan Mousavian, Yu Xiang, Dieter Fox
We evaluate the performance of our method for unseen object pose estimation on MOPED as well as the ModelNet and LINEMOD datasets.
1 code implementation • 22 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.
Robotics
3 code implementations • 23 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.
Robotics
no code implementations • 30 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.
1 code implementation • 22 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.
no code implementations • CVPR 2019 • Christopher Xie, Yu Xiang, Zaid Harchaoui, Dieter Fox
We consider the problem of providing dense segmentation masks for object discovery in videos.
8 code implementations • 27 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.
Robotics
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.
Ranked #1 on 6D Pose Estimation using RGB on YCB-Video
no code implementations • 7 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.
11 code implementations • 1 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.
Ranked #3 on 6D Pose Estimation using RGB on YCB-Video
1 code implementation • 9 Mar 2017 • Yu Xiang, Dieter Fox
3D scene understanding is important for robots to interact with the 3D world in a meaningful way.
1 code implementation • 16 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.
Ranked #4 on Vehicle Pose Estimation on KITTI Cars Hard
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.
Ranked #19 on Multiple Object Tracking on KITTI Tracking test
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.
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.
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.