1 code implementation • 18 Sep 2023 • Bowen Yin, Xuying Zhang, Zhongyu Li, Li Liu, Ming-Ming Cheng, Qibin Hou
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks.
Ranked #1 on
RGB-D Salient Object Detection
on DES
no code implementations • 24 Aug 2023 • Ziqi Yang, Zhongyu Li, Chen Liu, Xiangde Luo, Xingguang Wang, Dou Xu, CHAOQUN LI, Xiaoying Qin, Meng Yang, Long Jin
To make full use of pixel-level and cell-level features dynamically, we propose an asymmetric co-training framework combining a deep graph convolutional network and a convolutional neural network for multi-class histopathological image classification.
1 code implementation • 28 Feb 2023 • Yifan Zeng, Suiyi He, Han Hoang Nguyen, Yihan Li, Zhongyu Li, Koushil Sreenath, Jun Zeng
This work introduces a novel control strategy called Iterative Linear Quadratic Regulator for Iterative Tasks (i2LQR), which aims to improve closed-loop performance with local trajectory optimization for iterative tasks in a dynamic environment.
no code implementations • 19 Feb 2023 • Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world.
no code implementations • 10 Oct 2022 • Xiaoyu Huang, Zhongyu Li, Yanzhen Xiang, Yiming Ni, Yufeng Chi, Yunhao Li, Lizhi Yang, Xue Bin Peng, Koushil Sreenath
We present a reinforcement learning (RL) framework that enables quadrupedal robots to perform soccer goalkeeping tasks in the real world.
1 code implementation • 12 Sep 2022 • Gilbert Feng, Hongbo Zhang, Zhongyu Li, Xue Bin Peng, Bhuvan Basireddy, Linzhu Yue, Zhitao Song, Lizhi Yang, Yunhui Liu, Koushil Sreenath, Sergey Levine
In this work, we introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots.
no code implementations • 1 Aug 2022 • Yandong Ji, Zhongyu Li, Yinan Sun, Xue Bin Peng, Sergey Levine, Glen Berseth, Koushil Sreenath
Developing algorithms to enable a legged robot to shoot a soccer ball to a given target is a challenging problem that combines robot motion control and planning into one task.
no code implementations • 29 Jun 2022 • Chenyu Yang, Guo Ning Sue, Zhongyu Li, Lizhi Yang, Haotian Shen, Yufeng Chi, Akshara Rai, Jun Zeng, Koushil Sreenath
We develop and demonstrate one of the first collaborative autonomy framework that is able to move a cable-towed load, which is too heavy to move by a single robot, through narrow spaces with real-time feedback and reactive planning in experiments.
1 code implementation • 27 Jun 2022 • Yuchen Wang, Zhongyu Li, Xiangxiang Cui, Liangliang Zhang, Xiang Luo, Meng Yang, Shi Chang
Ultrasound examination is widely used in the clinical diagnosis of thyroid nodules (benign/malignant).
no code implementations • 30 May 2022 • Ashish Kumar, Zhongyu Li, Jun Zeng, Deepak Pathak, Koushil Sreenath, Jitendra Malik
In this work, we leverage recent advances in rapid adaptation for locomotion control, and extend them to work on bipedal robots.
no code implementations • 11 May 2022 • Zhongyu Li, Jun Zeng, Akshay Thirugnanam, Koushil Sreenath
Furthermore, we illustrate that the found linear model is able to provide guarantees by safety-critical optimal control framework, e. g., Model Predictive Control with Control Barrier Functions, on an example of autonomous navigation using Cassie while taking advantage of the agility provided by the RL-based controller.
no code implementations • 4 Mar 2022 • Lizhi Yang, Zhongyu Li, Jun Zeng, Koushil Sreenath
We leverage BO to learn the control parameters used in the HZD-based controller.
no code implementations • 4 Mar 2022 • Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown, Anca D. Dragan
As a result 1) all user feedback can contribute to learning about every emotion; 2) the robot can generate trajectories for any emotion in the space instead of only a few predefined ones; and 3) the robot can respond emotively to user-generated natural language by mapping it to a target VAD.
no code implementations • 13 Sep 2021 • Zhongyu Li, Jun Zeng, Shuxiao Chen, Koushil Sreenath
This demonstrates reliable autonomy to drive the robot to safely avoid obstacles while walking to the goal location in various kinds of height-constrained cluttered environments.
no code implementations • MICCAI Workshop COMPAY 2021 • CHAOQUN LI, Yitian Zhou, TangQi Shi, Yenan Wu, Meng Yang, Zhongyu Li
Meanwhile, we present a self-ensembling model to consider the source and the target domain together as a semi-supervised segmentation task to reduce the differences of outputs.
no code implementations • 1 Jul 2021 • Scott Gilroy, Derek Lau, Lizhi Yang, Ed Izaguirre, Kristen Biermayer, Anxing Xiao, Mengti Sun, Ayush Agrawal, Jun Zeng, Zhongyu Li, Koushil Sreenath
The resulted jumping mode is utilized in an autonomous navigation pipeline that leverages a search-based global planner and a local planner to enable the robot to reach the goal location by walking.
no code implementations • 28 May 2021 • Jingyi Liu, Zhongyu Li, Xiayue Fan, Jintao Yan, Bolin Li, Xuemeng Hu, Qing Xia, Yue Wu
Subsequently, a novel deep neural network, namely CRT-Net, is designed for the fine-grained and comprehensive representation and recognition of 1-D ECG signals.
2 code implementations • 21 May 2021 • Jun Zeng, Zhongyu Li, Koushil Sreenath
In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically.
no code implementations • 26 Mar 2021 • Zhongyu Li, Xuxin Cheng, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
Developing robust walking controllers for bipedal robots is a challenging endeavor.
no code implementations • 20 Mar 2021 • Jihua Zhu, Di Wang, Jiaxi Mu, Huimin Lu, Zhiqiang Tian, Zhongyu Li
Under the NDT framework, this paper proposes a novel multi-view registration method, named 3D multi-view registration based on the normal distributions transform (3DMNDT), which integrates the K-means clustering and Lie algebra solver to achieve multi-view registration.
1 code implementation • 13 Dec 2020 • Yanlin Ma, Jihua Zhu, Zhongyu Li, Zhiqiang Tian, Yaochen Li
What's more, the t-distribution takes the noise with heavy-tail into consideration, which makes the proposed method be inherently robust to noises and outliers.
no code implementations • 19 Oct 2020 • Qinghai Zheng, Yu Zhang, Jihua Zhu, Zhongyu Li, Haoyu Tang, Shuangxun Ma
It can be seen that specific information contained in different views is fully investigated by the rank preserving decomposition, and the high-order correlations of multi-view data are also mined by the low-rank tensor constraint.
1 code implementation • 19 Oct 2020 • Qinghai Zheng, Jihua Zhu, Yuanyuan Ma, Zhongyu Li, Zhiqiang Tian
Furthermore, underlying graph information of multi-view data is always ignored in most existing multi-view subspace clustering methods.
no code implementations • 12 Sep 2020 • Young-Ho Kim, Jarrod Collins, Zhongyu Li, Ponraj Chinnadurai, Ankur Kapoor, C. Huie Lin, Tommaso Mansi
We present a simplified calibration approach for error compensation and verify with complex rotation of the catheter in benchtop and phantom experiments under varying realistic curvature conditions.
no code implementations • 21 Aug 2020 • Dou Xu, Chang Cai, Chaowei Fang, Bin Kong, Jihua Zhu, Zhongyu Li
To thisend, we present a novel method for the unsupervised domain adaptationin histopathological image analysis, based on a backbone for embeddinginput images into a feature space, and a graph neural layer for propa-gating the supervision signals of images with labels.
Contrastive Learning
Histopathological Image Classification
+3
no code implementations • 7 Jul 2020 • Xinyuan Liu, Jihua Zhu, Qinghai Zheng, Zhongyu Li, Ruixin Liu, Jun Wang
More specifically, this novel loss function not only considers the mapping errors generated from the projection of the input space into the output one but also accounts for the reconstruction errors generated from the projection of the output space back to the input one.
no code implementations • 21 Apr 2020 • Jihua Zhu, Jie Hu, Huimin Lu, Badong Chen, Zhongyu Li
Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem.
no code implementations • 7 Apr 2020 • Qinghai Zheng, Jihua Zhu, Zhongyu Li, Shanmin Pang, Jun Wang, Lei Chen
The complementary graph regularizer investigates the specific information of multiple views.
no code implementations • 7 Apr 2020 • Qinghai Zheng, Jihua Zhu, Haoyu Tang, Xinyuan Liu, Zhongyu Li, Huimin Lu
Recently, label distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from labelel instances.
1 code implementation • 18 Feb 2020 • Jihua Zhu, Jing Zhang, Huimin Lu, Zhongyu Li
Registration of multi-view point sets is a prerequisite for 3D model reconstruction.
2 code implementations • 16 Oct 2019 • Peng Liu, Bin Kong, Zhongyu Li, Shaoting Zhang, Ruogu Fang
Our proposed CFEA is an interactive paradigm which presents an exquisite of collaborative adaptation through both adversarial learning and ensembling weights.
no code implementations • 30 Jun 2019 • Xinsheng Wang, Shanmin Pang, Jihua Zhu, Zhongyu Li, Zhiqiang Tian, Yaochen Li
The other is to optimize the visual feature structure in an intermediate embedding space, and in this method we successfully devise a multilayer perceptron framework based algorithm that is able to learn the common intermediate embedding space and meanwhile to make the visual data structure more distinctive.
1 code implementation • 19 Jun 2019 • Qinghai Zheng, Jihua Zhu, Zhiqiang Tian, Zhongyu Li, Shanmin Pang, Xiuyi Jia
Multi-view clustering is an important and fundamental problem.
1 code implementation • 30 Jan 2019 • Qinghai Zheng, Jihua Zhu, Zhongyu Li, Shanmin Pang, Jun Wang, Yaochen Li
To this end, this paper proposes a novel multi-view subspace clustering approach dubbed Feature Concatenation Multi-view Subspace Clustering (FCMSC), which boosts the clustering performance by exploring the consensus information of multi-view data.
no code implementations • 21 Apr 2018 • Jihua Zhu, Siyu Xu, Zutao Jiang, Shanmin Pang, Jun Wang, Zhongyu Li
This paper proposes a global approach for the multi-view registration of unordered range scans.
no code implementations • 20 Mar 2018 • Jiaxing Wang, Jihua Zhu, Shanmin Pang, Zhongyu Li, Yaochen Li, Xueming Qian
Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval.
no code implementations • 14 Jun 2017 • Zutao Jiang, Jihua Zhu, Yaochen Li, Zhongyu Li, Huimin Lu
The main idea of this approach is to recover all global motions for map merging from a set of relative motions.
no code implementations • 1 Jun 2017 • Congcong Jin, Jihua Zhu, Yaochen Li, Shaoyi Du, Zhongyu Li, Huimin Lu
For the registration of partially overlapping point clouds, this paper proposes an effective approach based on both the hard and soft assignments.
no code implementations • 21 Feb 2017 • Rui Guo, Jihua Zhu, Yaochen Li, Dapeng Chen, Zhongyu Li, Yongqin Zhang
With the overlapping percentage available, it views the overlapping percentage as the corresponding weight of each scan pair and proposes the weight motion averaging algorithm, which can pay more attention to reliable and accurate relative motions.