no code implementations • 28 Jan 2025 • Yun Li, Zhe Liu, Yajing Kong, Guangrui Li, Jiyuan Zhang, Chao Bian, Feng Liu, Lina Yao, Zhenbang Sun
Using STE, we systematically compare implicit and explicit temporal modeling across dimensions such as overall performance, token compression effectiveness, and temporal-specific understanding.
1 code implementation • 25 Dec 2024 • Yuchen Ren, Zhengyu Zhao, Chenhao Lin, Bo Yang, Lu Zhou, Zhe Liu, Chao Shen
We propose the Multiple Monotonic Diversified Integrated Gradients (MuMoDIG) attack, which can generate highly transferable adversarial examples on different CNN and ViT models and defenses.
no code implementations • 22 Dec 2024 • Huiwen Wu, Deyi Zhang, Xiaohan Li, Xiaogang Xu, Jiafei Wu, Zhe Liu
The second stage is to fine-tune the overall LLM with a differential privacy guarantee by adopting appropriate Gaussian noises.
1 code implementation • 18 Dec 2024 • Yang Pu, Zhiyuan Dai, Yifan Zhou, Ning Jia, Hongyue Wang, Yerzhan Mukhametkarimov, Ruihao Chen, Hongqiang Wang, Zhe Liu
Machine learning (ML) has been extensively employed in planar perovskite photovoltaics to screen effective organic molecular additives, while encountering predictive biases for novel materials due to small datasets and reliance on predefined descriptors.
no code implementations • 10 Dec 2024 • Yun Li, Zhe Liu, Lina Yao
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of seen attributes and objects.
no code implementations • 9 Dec 2024 • Yingyi Ma, Zhe Liu, Ozlem Kalinli
The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
no code implementations • 30 Nov 2024 • Yiyuan Pan, Yunzhe Xu, Zhe Liu, Hesheng Wang
This system enables agents to maintain and expand their memory through both imaginative mechanisms and navigation actions.
no code implementations • 24 Nov 2024 • Haoang Li, Xiangqi Meng, Xingxing Zuo, Zhe Liu, Hesheng Wang, Daniel Cremers
Our method is composed of three main modules to 1) map the dynamic foreground including non-rigid humans and rigid items, 2) reconstruct the static background, and 3) localize the camera.
no code implementations • 31 Oct 2024 • Chiyu Zhang, Xiaogang Xu, Jiafei Wu, Zhe Liu, Lu Zhou
Adversarial attacks, which manipulate input data to undermine model availability and integrity, pose significant security threats during machine learning inference.
no code implementations • 24 Oct 2024 • Yating Ma, Xiaogang Xu, Liming Fang, Zhe Liu
Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN).
no code implementations • 16 Oct 2024 • Huiwen Wu, Xiaohan Li, Xiaogang Xu, Jiafei Wu, Deyi Zhang, Zhe Liu
By leveraging the differences between these two models, we create a more straightforward pathway to eliminate hallucinations, and the iterative nature of contrastive learning further enhances performance.
no code implementations • 17 Sep 2024 • Hao Fang, Zhe Liu, Yi Feng, Zhen Qiu, Pierre Bagnaninchi, Yunjie Yang
Moreover, the dependency on training data in supervised MMV methods can introduce erroneous conductivity contrasts across frequencies, posing significant concerns in biomedical applications.
no code implementations • 8 Sep 2024 • Zhiwei Lin, Zhe Liu, Yongtao Wang, Le Zhang, Ce Zhu
Secondly, the CAMF module utilizes a deformable attention mechanism to align radar and camera BEV features and adopts channel and spatial fusion layers to fuse them.
Ranked #1 on
3D Object Detection
on nuscenes Camera-Radar
1 code implementation • 1 Sep 2024 • Haojian Huang, Chuanyu Qin, Zhe Liu, Kaijing Ma, Jin Chen, Han Fang, Chao Ban, Hao Sun, Zhongjiang He
This method effectively integrates local and global feature-neighborhood (F-N) structures for robust decision-making.
no code implementations • 23 Aug 2024 • Haojian Huang, Zhe Liu, Sukumar Letchmunan, Muhammet Deveci, Mingwei Lin, Weizhong Wang
Incomplete multi-view data classification poses significant challenges due to the common issue of missing views in real-world scenarios.
1 code implementation • 23 Aug 2024 • Zhe Liu, Xiang Huang, Jingyun Zhang, Zhifeng Hao, Li Sun, Hao Peng
Additionally, we present an augmented GAT to manage complex inter-feature dependencies, which incorporates graph topology into node features across multiple scales, a versatile, plug-and-play enhancement that significantly boosts the performance of GAT.
1 code implementation • 20 Aug 2024 • Yunzhe Xu, Yiyuan Pan, Zhe Liu, Hesheng Wang
Large Language Models (LLMs) have demonstrated potential in Vision-and-Language Navigation (VLN) tasks, yet current applications face challenges.
Ranked #1 on
Vision and Language Navigation
on map2seq
no code implementations • 19 Aug 2024 • Puning Zhao, Jiafei Wu, Zhe Liu, Chong Wang, Rongfei Fan, Qingming Li
The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting in a superfluous factor of $d$ in the union bound.
no code implementations • 19 Aug 2024 • Puning Zhao, Jiafei Wu, Zhe Liu, Huiwen Wu
In this paper, we solve the nonparametric contextual bandit problem with unbounded contexts.
no code implementations • 31 Jul 2024 • Zhe Liu, Xiliang Zhu, Tong Han, Yuhao Huang, Jian Wang, Lian Liu, Fang Wang, Dong Ni, Zhongshan Gou, Xin Yang
Since MR data is limited and has large intra-class variability, we propose an unsupervised out-of-distribution (OOD) detection method to identify MR rather than building a deep classifier.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
1 code implementation • 25 Jul 2024 • Zhe Liu, Jinghua Hou, Xinyu Wang, Xiaoqing Ye, Jingdong Wang, Hengshuang Zhao, Xiang Bai
To tackle this problem, we simply introduce a 3D spatial feature descriptor and integrate it into the linear group RNN operators to enhance their spatial features rather than blindly increasing the number of scanning orders for voxel features.
Ranked #1 on
3D Object Detection
on Waymo Open Dataset
1 code implementation • 15 Jul 2024 • Zhe Liu, Jinghua Hou, Xiaoqing Ye, Tong Wang, Jingdong Wang, Xiang Bai
We argue that the main challenges are twofold: 1) How to obtain the appropriate object queries is challenging due to the high sparsity and uneven distribution of point clouds; 2) How to implement an effective query interaction by exploiting the rich geometric structure of point clouds is not fully explored.
1 code implementation • 15 Jul 2024 • Jinghua Hou, Tong Wang, Xiaoqing Ye, Zhe Liu, Shi Gong, Xiao Tan, Errui Ding, Jingdong Wang, Xiang Bai
Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection.
no code implementations • 27 May 2024 • Puning Zhao, Li Shen, Rongfei Fan, Qingming Li, Huiwen Wu, Jiafei Wu, Zhe Liu
Under the central model, user-level DP is strictly stronger than the item-level one.
no code implementations • 24 May 2024 • Puning Zhao, Rongfei Fan, Huiwen Wu, Qingming Li, Jiafei Wu, Zhe Liu
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public.
no code implementations • 24 May 2024 • Lichuan Ji, Yingqi Lin, Zhenhua Huang, Yan Han, Xiaogang Xu, Jiafei Wu, Chong Wang, Zhe Liu
Current datasets lack a varied and comprehensive repository of real and generated content for effective discrimination.
no code implementations • 23 May 2024 • Jiuming Liu, Jinru Han, Lihao Liu, Angelica I. Aviles-Rivero, Chaokang Jiang, Zhe Liu, Hesheng Wang
Point cloud videos can faithfully capture real-world spatial geometries and temporal dynamics, which are essential for enabling intelligent agents to understand the dynamically changing world.
no code implementations • 22 May 2024 • Huiwen Wu, Xiaohan Li, Deyi Zhang, Xiaogang Xu, Jiafei Wu, Puning Zhao, Zhe Liu
The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL).
no code implementations • 22 May 2024 • Puning Zhao, Lifeng Lai, Li Shen, Qingming Li, Jiafei Wu, Zhe Liu
We provide a theoretical analysis of our approach, which gives the noise strength needed for privacy protection, as well as the bound of mean squared error.
no code implementations • 7 Apr 2024 • Jinyi Xu, Zuowei Zhang, Ze Lin, Yixiang Chen, Zhe Liu, Weiping Ding
Moreover, if an object is in the overlapping region of several singleton clusters, it can be assigned to a meta-cluster, defined as the union of these singleton clusters, to characterize the local imprecision in the result.
1 code implementation • 27 Mar 2024 • Jiuming Liu, Dong Zhuo, Zhiheng Feng, Siting Zhu, Chensheng Peng, Zhe Liu, Hesheng Wang
Image pixels are pre-organized as pseudo points for image-to-point structure alignment.
1 code implementation • CVPR 2024 • Zhiwei Lin, Zhe Liu, Zhongyu Xia, Xinhao Wang, Yongtao Wang, Shengxiang Qi, Yang Dong, Nan Dong, Le Zhang, Ce Zhu
In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two encoders.
Ranked #4 on
3D Object Detection (RoI)
on View-of-Delft (val)
no code implementations • 18 Mar 2024 • Wenhua Wu, Qi Wang, Guangming Wang, JunPing Wang, Tiankun Zhao, Yang Liu, Dongchao Gao, Zhe Liu, Hesheng Wang
To address this, we propose EMIE-MAP, a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding.
1 code implementation • 12 Mar 2024 • Ronald B. Liu, Zhe Liu, Max G. A. Wolf, Krishna P. Purohit, Gregor Fritz, Yi Feng, Carsten G. Hansen, Pierre O. Bagnaninchi, Xavier Casadevall i Solvas, Yunjie Yang
Advancements in high-throughput biomedical applications necessitate real-time, large field-of-view (FOV) imaging capabilities.
no code implementations • CVPR 2024 • Xiaogang Xu, Shu Kong, Tao Hu, Zhe Liu, Hujun Bao
Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions.
1 code implementation • 27 Feb 2024 • Hongcheng Yang, Dingkang Liang, Dingyuan Zhang, Zhe Liu, Zhikang Zou, Xingyu Jiang, Yingying Zhu
For such purpose, this paper presents an advanced sampler that achieves both high accuracy and efficiency.
Ranked #3 on
3D Part Segmentation
on ShapeNet-Part
no code implementations • CVPR 2024 • Yun Li, Zhe Liu, Hang Chen, Lina Yao
Our framework evaluates the specificity of attributes by considering the diversity of objects they apply to and their related context.
no code implementations • 27 Jan 2024 • Kaixin Xiong, Dingyuan Zhang, Dingkang Liang, Zhe Liu, Hongcheng Yang, Wondimu Dikubab, Jianwei Cheng, Xiang Bai
Monocular 3D Object Detection is an essential task for autonomous driving.
1 code implementation • CVPR 2024 • Jiuming Liu, Guangming Wang, Weicai Ye, Chaokang Jiang, Jinru Han, Zhe Liu, Guofeng Zhang, Dalong Du, Hesheng Wang
Furthermore we also develop an uncertainty estimation module within diffusion to evaluate the reliability of estimated scene flow.
no code implementations • 26 Dec 2023 • Yan Han, Xiaogang Xu, Yingqi Lin, Jiafei Wu, Zhe Liu
In existing Video Frame Interpolation (VFI) approaches, the motion estimation between neighboring frames plays a crucial role.
no code implementations • 26 Dec 2023 • Yingqi Lin, Xiaogang Xu, Yan Han, Jiafei Wu, Zhe Liu
First, a depth-aware feature extraction module is designed to inject depth priors into the image representation.
1 code implementation • 29 Nov 2023 • Jiuming Liu, Guangming Wang, Weicai Ye, Chaokang Jiang, Jinru Han, Zhe Liu, Guofeng Zhang, Dalong Du, Hesheng Wang
Furthermore, we also develop an uncertainty estimation module within diffusion to evaluate the reliability of estimated scene flow.
no code implementations • 17 Oct 2023 • Yingyi Ma, Zhe Liu, Ozlem Kalinli
Language models (LMs) have been commonly adopted to boost the performance of automatic speech recognition (ASR) particularly in domain adaptation tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
no code implementations • 1 Oct 2023 • Qiannan Wang, Changchun Yin, Zhe Liu, Liming Fang, Run Wang, Chenhao Lin
Pre-trained image encoders can serve as feature extractors, facilitating the construction of downstream classifiers for various tasks.
no code implementations • 28 Sep 2023 • Zhe Liu, Ozlem Kalinli
Recent research has shown that language models have a tendency to memorize rare or unique token sequences in the training corpus.
no code implementations • 12 Sep 2023 • Arpita Vats, Zhe Liu, Peng Su, Debjyoti Paul, Yingyi Ma, Yutong Pang, Zeeshan Ahmed, Ozlem Kalinli
To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where downstream natural language processing (NLP) models can be directly trained using such in-domain data.
no code implementations • 7 Sep 2023 • Luping Rao, Chuan Ma, Ming Ding, Yuwen Qian, Lu Zhou, Zhe Liu
However, the current object detection methods are mostly based on centralized deep training, that is, the sensitive data obtained by edge devices need to be uploaded to the server, which raises privacy concerns.
no code implementations • 5 Sep 2023 • Xin Zhou, Jinghua Hou, Tingting Yao, Dingkang Liang, Zhe Liu, Zhikang Zou, Xiaoqing Ye, Jianwei Cheng, Xiang Bai
3D object detection is an essential task for achieving autonomous driving.
no code implementations • 1 Sep 2023 • Chuanneng Sun, Zeeshan Ahmed, Yingyi Ma, Zhe Liu, Lucas Kabela, Yutong Pang, Ozlem Kalinli
We propose to leverage prompts for a LLM without fine tuning during rescoring which incorporate a biasing list and few-shot examples to serve as additional information when calculating the score for the hypothesis.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
no code implementations • 16 Aug 2023 • Han Zhou, Dong Ni, Ao Chang, Xinrui Zhou, Rusi Chen, Yanlin Chen, Lian Liu, Jiamin Liang, Yuhao Huang, Tong Han, Zhe Liu, Deng-Ping Fan, Xin Yang
Second, to better preserve the integrity and textural information of US images, we implemented a dual-decoder that decouples the content and textural features in the generator.
1 code implementation • ICCV 2023 • Chang Nie, Guangming Wang, Zhe Liu, Luca Cavalli, Marc Pollefeys, Hesheng Wang
Therefore, RLSAC can avoid differentiating to learn the features and the feedback of downstream tasks for end-to-end robust estimation.
no code implementations • 20 Jun 2023 • Guangming Wang, Yu Zheng, Yanfeng Guo, Zhe Liu, Yixiang Zhu, Wolfram Burgard, Hesheng Wang
A popular approach to robot localization is based on image-to-point cloud registration, which combines illumination-invariant LiDAR-based mapping with economical image-based localization.
1 code implementation • 4 Jun 2023 • Dingyuan Zhang, Dingkang Liang, Hongcheng Yang, Zhikang Zou, Xiaoqing Ye, Zhe Liu, Xiang Bai
In the spirit of unleashing the capability of foundation models on vision tasks, the Segment Anything Model (SAM), a vision foundation model for image segmentation, has been proposed recently and presents strong zero-shot ability on many downstream 2D tasks.
1 code implementation • 29 May 2023 • Zhen Zhang, Mengting Hu, Shiwan Zhao, Minlie Huang, Haotian Wang, Lemao Liu, Zhirui Zhang, Zhe Liu, Bingzhe Wu
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments.
1 code implementation • 12 May 2023 • Zhe Liu, Xiaoqing Ye, Zhikang Zou, Xinwei He, Xiao Tan, Errui Ding, Jingdong Wang, Xiang Bai
Extensive experiments on the nuScenes dataset demonstrate that our method is much more stable in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods.
Ranked #48 on
3D Object Detection
on nuScenes
no code implementations • 4 Apr 2023 • Wenxuan Tu, Qing Liao, Sihang Zhou, Xin Peng, Chuan Ma, Zhe Liu, Xinwang Liu, Zhiping Cai
To address this issue, we propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space.
no code implementations • 30 Mar 2023 • Zhe Liu, Zhou Chen, Qi Wang, Sheng Zhang, Yunjie Yang
The results suggest that combining the shallow image prior and the hand-crafted regularization can achieve similar performance to the Deep Image Prior (DIP) but with less architectural dependency and complexity of the neural network.
1 code implementation • ICCV 2023 • Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Marc Pollefeys, Hesheng Wang
Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers by extracting point features globally.
no code implementations • 10 Mar 2023 • Xiuxiu Bai, Shuaishuai Zhao, Yao Gao, Zhe Liu
We verify this theory through simulation experiments and demonstrate the mode-locking pattern in real-world scene models.
1 code implementation • 9 Mar 2023 • Jingyu Li, Zhe Liu, Jinghua Hou, Dingkang Liang
In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D.
no code implementations • ICCV 2023 • Yun Li, Zhe Liu, Saurav Jha, Sally Cripps, Lina Yao
Open-World Compositional Zero-Shot Learning (OW-CZSL) aims to recognize new compositions of seen attributes and objects.
no code implementations • 27 Feb 2023 • Guodong Huang, Chuan Ma, Ming Ding, Yuwen Qian, Chunpeng Ge, Liming Fang, Zhe Liu
To achieve a configurable trade-off between the defense and the network overhead, we further improve the list-based defense by a traffic splitting mechanism, which can combat the mentioned attacks as well as save a considerable amount of network overhead.
1 code implementation • 21 Jan 2023 • Xinhang Wan, Xinwang Liu, Jiyuan Liu, Siwei Wang, Yi Wen, Weixuan Liang, En Zhu, Zhe Liu, Lu Zhou
Multi-view clustering has gained broad attention owing to its capacity to exploit complementary information across multiple data views.
no code implementations • 4 Jan 2023 • Zhe Liu, Xiaoqing Ye, Xiao Tan, Errui Ding, Xiang Bai
In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation.
no code implementations • ICCV 2023 • Dingyuan Zhang, Dingkang Liang, Zhikang Zou, Jingyu Li, Xiaoqing Ye, Zhe Liu, Xiao Tan, Xiang Bai
Advanced 3D object detection methods usually rely on large-scale, elaborately labeled datasets to achieve good performance.
no code implementations • 9 Nov 2022 • Yingyi Ma, Zhe Liu, Xuedong Zhang
Thus, the data sampling strategy is important to the adaptation performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
1 code implementation • 8 Nov 2022 • Dian Qin, Haishuai Wang, Zhe Liu, Hongjia Xu, Sheng Zhou, Jiajun Bu
Since the distilled 2D networks are supervised by the curves converted from dimensionally heterogeneous 3D features, the 2D networks are given an informative view in terms of learning structural information embedded in well-trained high-dimensional representations.
no code implementations • 5 Nov 2022 • Zhe Liu, Yun Li, Lina Yao, Xiaojun Chang, Wei Fang, XiaoJun Wu, Yi Yang
We design Semantic Attention (SA) and generative Knowledge Disentanglement (KD) to learn the dependence of feasibility and contextuality, respectively.
no code implementations • 13 Oct 2022 • Zhe Liu, Xuedong Zhang, Fuchun Peng
Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data.
no code implementations • 4 Oct 2022 • Zhe Liu, Yue Hui, Fuchun Peng
Federated learning (FL) can help promote data privacy by training a shared model in a de-centralized manner on the physical devices of clients.
no code implementations • 7 Sep 2022 • Zhe Liu, Fuchun Peng
In this paper, we present graphical lasso based methods to explicitly model such dependency and estimate uncorrelated blocks of utterances in a rigorous way, after which blockwise bootstrap is applied on top of the inferred blocks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
no code implementations • 5 Sep 2022 • Yundi Shi, Piji Li, Changchun Yin, Zhaoyang Han, Lu Zhou, Zhe Liu
Therefore, in this paper, we propose a malicious prompt template construction method (\textbf{PromptAttack}) to probe the security performance of PLMs.
no code implementations • 1 Aug 2022 • Jan Blumenkamp, QingBiao Li, Binyu Wang, Zhe Liu, Amanda Prorok
We consider the problem of navigating a mobile robot towards a target in an unknown environment that is endowed with visual sensors, where neither the robot nor the sensors have access to global positioning information and only use first-person-view images.
1 code implementation • 19 Jul 2022 • Guangming Wang, Yunzhe Hu, Zhe Liu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang
Our proposed model surpasses all existing methods by at least 38. 2% on FlyingThings3D dataset and 24. 7% on KITTI Scene Flow dataset for EPE3D metric.
no code implementations • 14 Jun 2022 • Siyu Isaac Parker Tian, Zekun Ren, Selvaraj Venkataraj, Yuanhang Cheng, Daniil Bash, Felipe Oviedo, J. Senthilnath, Vijila Chellappan, Yee-Fun Lim, Armin G. Aberle, Benjamin P MacLeod, Fraser G. L. Parlane, Curtis P. Berlinguette, Qianxiao Li, Tonio Buonassisi, Zhe Liu
Transfer learning increasingly becomes an important tool in handling data scarcity often encountered in machine learning.
no code implementations • 2 Jun 2022 • Jianhong Han, Zhaoyi Wan, Zhe Liu, Jie Feng, Bingfeng Zhou
We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.
no code implementations • 20 May 2022 • Bingzhe Wu, Jintang Li, Junchi Yu, Yatao Bian, Hengtong Zhang, Chaochao Chen, Chengbin Hou, Guoji Fu, Liang Chen, Tingyang Xu, Yu Rong, Xiaolin Zheng, Junzhou Huang, Ran He, Baoyuan Wu, Guangyu Sun, Peng Cui, Zibin Zheng, Zhe Liu, Peilin Zhao
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery.
no code implementations • 20 May 2022 • Xiuxiu Bai, Zhe Liu, Yao Gao, Bin Liu, Yongqiang Hao
Artificial neural networks have realized incredible successes at image recognition, but the underlying mechanism of visual space representation remains a huge mystery.
no code implementations • 3 May 2022 • Yun Li, Zhe Liu, Lina Yao, Jessica J. M. Monaghan, David Mcalpine
The side-aware unsupervised domain adaptation module adapts the class-irrelevant information as domain variance to a new dataset and excludes the variance to obtain the class-distill features for the new dataset classification.
no code implementations • 3 May 2022 • Yun Li, Zhe Liu, Lina Yao, Molly Lucas, Jessica J. M. Monaghan, Yu Zhang
With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses.
1 code implementation • 4 Apr 2022 • Shengyuan Hu, Jack Goetz, Kshitiz Malik, Hongyuan Zhan, Zhe Liu, Yue Liu
Model compression is important in federated learning (FL) with large models to reduce communication cost.
no code implementations • 28 Jan 2022 • Antoine Bruguier, Duc Le, Rohit Prabhavalkar, Dangna Li, Zhe Liu, Bo wang, Eun Chang, Fuchun Peng, Ozlem Kalinli, Michael L. Seltzer
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework.
no code implementations • ACM 2022 • Zhe Liu, Weijie Xia, Yongzhen Lei
Finally, We design a series of simulation and experiment to verify the effectiveness of the adversarial examples and also the modulation sequences.
no code implementations • 6 Jan 2022 • Yun Li, Zhe Liu, Xiaojun Chang, Julian McAuley, Lina Yao
We further propose a differentiable dataset-level balance and update the weights in a linear annealing schedule to simulate network pruning and thus obtain the optimal structure for BSNet with dataset-level balance achieved.
1 code implementation • 21 Dec 2021 • Zhe Liu, Tengteng Huang, Bingling Li, Xiwu Chen, Xi Wang, Xiang Bai
Recently, fusing the LiDAR point cloud and camera image to improve the performance and robustness of 3D object detection has received more and more attention, as these two modalities naturally possess strong complementarity.
1 code implementation • 9 Dec 2021 • Silin Cheng, Xiwu Chen, Xinwei He, Zhe Liu, Xiang Bai
Learning intra-region contexts and inter-region relations are two effective strategies to strengthen feature representations for point cloud analysis.
Ranked #45 on
3D Point Cloud Classification
on ModelNet40
no code implementations • 6 Dec 2021 • Guangming Wang, Jiquan Zhong, Shijie Zhao, Wenhua Wu, Zhe Liu, Hesheng Wang
In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer.
no code implementations • 1 Dec 2021 • Zhe Liu, Yun Li, Lina Yao, Julian McAuley, Sam Dixon
Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings, which demonstrates the effectiveness of spiral learning in learning generalizable and complex correlations.
1 code implementation • 3 Nov 2021 • Guangming Wang, Xinrui Wu, Shuyang Jiang, Zhe Liu, Hesheng Wang
An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper.
no code implementations • 3 Nov 2021 • Yun Li, Zhe Liu, Lina Yao, Xianzhi Wang, Julian McAuley, Xiaojun Chang
Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations.
no code implementations • 8 Oct 2021 • Rishi E. Kumar, Armi Tiihonen, Shijing Sun, David P. Fenning, Zhe Liu, Tonio Buonassisi
While halide perovskites attract significant academic attention, examples of at-scale industrial production are still sparse.
1 code implementation • 1 Oct 2021 • Zhe Liu, Nicholas Rolston, Austin C. Flick, Thomas W. Colburn, Zekun Ren, Reinhold H. Dauskardt, Tonio Buonassisi
With a limited experimental budget of screening 100 process conditions, we demonstrated an efficiency improvement to 18. 5% as the best-in-our-lab device fabricated by RSPP, and we also experimentally found 10 unique process conditions to produce the top-performing devices of more than 17% efficiency, which is 5 times higher rate of success than the control experiments with pseudo-random Latin hypercube sampling.
no code implementations • 28 Sep 2021 • Zhe Liu, Ke Li, Shreyan Bakshi, Fuchun Peng
Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
no code implementations • 19 Sep 2021 • Zhe Liu, Irina-Elena Veliche, Fuchun Peng
The issue of fairness arises when the automatic speech recognition (ASR) systems do not perform equally well for all subgroups of the population.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
1 code implementation • 23 Aug 2021 • Dian Qin, Jiajun Bu, Zhe Liu, Xin Shen, Sheng Zhou, Jingjun Gu, Zhijua Wang, Lei Wu, Huifen Dai
To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network.
1 code implementation • 15 Aug 2021 • Mahdi S. Hosseini, Jia Shu Zhang, Zhe Liu, Andre Fu, Jingxuan Su, Mathieu Tuli, Sepehr Hosseini, Arsh Kadakia, Haoran Wang, Konstantinos N. Plataniotis
To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN.
no code implementations • 26 Jul 2021 • Amanda Prorok, Jan Blumenkamp, QingBiao Li, Ryan Kortvelesy, Zhe Liu, Ethan Stump
Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances.
no code implementations • 28 Jun 2021 • Guangming Wang, Honghao Zeng, Ziliang Wang, Zhe Liu, Hesheng Wang
Ablation studies demonstrate the effectiveness of the proposed inter-frame projection consistency constraints and intra-frame loop constraints.
Ranked #51 on
3D Human Pose Estimation
on Human3.6M
no code implementations • CVPR 2021 • Haoang Li, Kai Chen, Ji Zhao, Jiangliu Wang, Pyojin Kim, Zhe Liu, Yun-hui Liu
In contrast, we propose the first approach suitable for both structured and unstructured scenes.
no code implementations • 15 Jun 2021 • Zhe Liu, Pierre Bagnaninchi, Yunjie Yang
While Electrical Impedance Tomography (EIT) has found many biomedicine applications, a better resolution is needed to provide quantitative analysis for tissue engineering and regenerative medicine.
no code implementations • 2 Jun 2021 • Zhe Liu, Yufan Guo, Jalal Mahmud
Although deep neural networks have been widely employed and proven effective in sentiment analysis tasks, it remains challenging for model developers to assess their models for erroneous predictions that might exist prior to deployment.
no code implementations • NAACL 2021 • Zhe Liu, Yufan Guo, Jalal Mahmud
Although deep neural networks have been widely employed and proven effective in sentiment analysis tasks, it remains challenging for model developers to assess their models for erroneous predictions that might exist prior to deployment.
no code implementations • 1 Jun 2021 • Zhe Liu, Yibin Xu
In this work, we propose a novel Transformer with Hyperbolic Geometry (THG) model, which take the advantage of both Euclidean space and Hyperbolic space.
1 code implementation • 23 May 2021 • Qiaohao Liang, Aldair E. Gongora, Zekun Ren, Armi Tiihonen, Zhe Liu, Shijing Sun, James R. Deneault, Daniil Bash, Flore Mekki-Berrada, Saif A. Khan, Kedar Hippalgaonkar, Benji Maruyama, Keith A. Brown, John Fisher III, Tonio Buonassisi
In the field of machine learning (ML) for materials optimization, active learning algorithms, such as Bayesian Optimization (BO), have been leveraged for guiding autonomous and high-throughput experimentation systems.
no code implementations • NAACL (TrustNLP) 2021 • Amita Misra, Zhe Liu, Jalal Mahmud
Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks.
no code implementations • 22 Apr 2021 • Yun Li, Zhe Liu, Lina Yao, Xiaojun Chang
The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards seen classes.
no code implementations • 3 Mar 2021 • Zhe Liu, Yun Li, Lina Yao, Xianzhi Wang, Guodong Long
Zero-shot learning (ZSL) refers to the problem of learning to classify instances from the novel classes (unseen) that are absent in the training set (seen).
no code implementations • ICCV 2021 • Haoang Li, Kai Chen, Pyojin Kim, Kuk-Jin Yoon, Zhe Liu, Kyungdon Joo, Yun-hui Liu
Based on this map, we can detect all the VPs.
no code implementations • 28 Dec 2020 • Zhen Li, Sunzeng Cai, Xiaoyi Wang, Zhe Liu, Nian Xue
Multiple Object Tracking (MOT) has been a useful yet challenging task in many real-world applications such as video surveillance, intelligent retail, and smart city.
no code implementations • 20 Dec 2020 • Guangming Wang, Muyao Chen, Hanwen Liu, Yehui Yang, Zhe Liu, Hesheng Wang
Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points.
1 code implementation • 9 Dec 2020 • Zhijian Qiao, Hanjiang Hu, Weiang Shi, Siyuan Chen, Zhe Liu, Hesheng Wang
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance.
no code implementations • 5 Dec 2020 • Xiuxiu Bai, Lele Ye, Zhe Liu
Detecting object skeletons in natural images presents challenging, due to varied object scales, the complexity of backgrounds and various noises.
1 code implementation • CVPR 2021 • Guangming Wang, Xinrui Wu, Zhe Liu, Hesheng Wang
A novel 3D point cloud learning model for deep LiDAR odometry, named PWCLO-Net, using hierarchical embedding mask optimization is proposed in this paper.
1 code implementation • COLING 2020 • Huiwei Zhou, Yibin Xu, Weihong Yao, Zhe Liu, Chengkun Lang, Haibin Jiang
In this paper, we propose Global Context-enhanced Graph Convolutional Networks (GCGCN), a novel model which is composed of entities as nodes and context of entity pairs as edges between nodes to capture rich global context information of entities in a document.
no code implementations • 1 Dec 2020 • Zhe Liu, Fuchun Peng
Our presented approach can overcome the limitations of federated fine-tuning and efficiently learn personalized NNLMs on devices.
1 code implementation • 30 Nov 2020 • Zhijian Qiao, Huanshu Wei, Zhe Liu, Chuanzhe Suo, Hesheng Wang
3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information.
no code implementations • 27 Nov 2020 • Mingfu Xue, Can He, Zhiyu Wu, Jian Wang, Zhe Liu, Weiqiang Liu
on person stealth attacks, and propose 3D transformations to generate 3D invisible cloak.
no code implementations • 27 Nov 2020 • Guangming Wang, Yehui Yang, Huixin Zhang, Zhe Liu, Hesheng Wang
In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator.
1 code implementation • 26 Nov 2020 • QingBiao Li, Weizhe Lin, Zhe Liu, Amanda Prorok
Our Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots.
no code implementations • 24 Nov 2020 • Guangming Wang, Minjian Xin, Wenhua Wu, Zhe Liu, Hesheng Wang
Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end.
no code implementations • 12 Oct 2020 • Guangming Wang, Xinrui Wu, Zhe Liu, Hesheng Wang
In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer.
1 code implementation • 1 Oct 2020 • Hanjiang Hu, Zhijian Qiao, Ming Cheng, Zhe Liu, Hesheng Wang
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc.
1 code implementation • 16 Sep 2020 • Hanjiang Hu, Hesheng Wang, Zhe Liu, Weidong Chen
Visual localization is a crucial component in the application of mobile robot and autonomous driving.
1 code implementation • ECCV 2020 • Tengteng Huang, Zhe Liu, Xiwu Chen, Xiang Bai
In this paper, we aim at addressing two critical issues in the 3D detection task, including the exploitation of multiple sensors~(namely LiDAR point cloud and camera image), as well as the inconsistency between the localization and classification confidence.
no code implementations • 14 Jul 2020 • Zhe Liu, Xianzhi Wang, Lina Yao, Jake An, Lei Bai, Ee-Peng Lim
We design a semi-supervised model based on a hierarchical embedding network to extract high-level features of consumers and to predict the top-$N$ purchase destinations of a consumer.
1 code implementation • 14 Jul 2020 • Zhe Liu, Lina Yao, Lei Bai, Xianzhi Wang, Can Wang
It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class.
no code implementations • 12 May 2020 • Zhe Liu, Yun Li, Lina Yao, Xianzhi Wang, Feiping Nie
Conventional multi-view clustering methods seek for a view consensus through minimizing the pairwise discrepancy between the consensus and subviews.
1 code implementation • 11 May 2020 • Binyu Wang, Zhe Liu, Qing-Biao Li, Amanda Prorok
Path planning for mobile robots in large dynamic environments is a challenging problem, as the robots are required to efficiently reach their given goals while simultaneously avoiding potential conflicts with other robots or dynamic objects.
no code implementations • 18 Apr 2020 • Zhe Liu, Lina Yao, Xianzhi Wang, Lei Bai, Jake An
Most current studies on survey analysis and risk tolerance modelling lack professional knowledge and domain-specific models.
no code implementations • 19 Dec 2019 • Zhe Liu, Fuchun Peng
A common question being raised in automatic speech recognition (ASR) evaluations is how reliable is an observed word error rate (WER) improvement comparing two ASR systems, where statistical hypothesis testing and confidence interval (CI) can be utilized to tell whether this improvement is real or only due to random chance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
2 code implementations • 11 Dec 2019 • Zhe Liu, Xin Zhao, Tengteng Huang, Ruolan Hu, Yu Zhou, Xiang Bai
In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches.
no code implementations • 29 Nov 2019 • Jing Xiao, Hualin Zhan, Zaiquan Xu, Xiao Wang, Ke Zhang, Zhiyuan Xiong, George P. Simon, Zhe Liu, Dan Li
Multilayered graphene-based nanoporous membranes with electrolyte incorporated between individual sheets is a unique nano-heterostructure system in which nanoconfined electrons in graphene and ions confined in between sheets are intimately coupled throughout the entire membrane.
Mesoscale and Nanoscale Physics Materials Science Soft Condensed Matter Applied Physics Chemical Physics
no code implementations • 22 Nov 2019 • Yiren Wang, Hongzhao Huang, Zhe Liu, Yutong Pang, Yongqiang Wang, ChengXiang Zhai, Fuchun Peng
Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference.
no code implementations • 25 Sep 2019 • Yash Bhalgat, Zhe Liu, Pritam Gundecha, Jalal Mahmud, Amita Misra
Given that labeled data is expensive to obtain in real-world scenarios, many semi-supervised algorithms have explored the task of exploitation of unlabeled data.
1 code implementation • 23 Sep 2019 • Hanjiang Hu, Hesheng Wang, Zhe Liu, Chenguang Yang, Weidong Chen, Le Xie
To retrieve a target image from the database, the query image is first encoded using the encoder belonging to the query domain to obtain a domain-invariant feature vector.
1 code implementation • 18 Sep 2019 • Xiang Zhang, Lina Yao, Manqing Dong, Zhe Liu, Yu Zhang, Yong Li
Furthermore, to enhance the explainability, we develop an attention mechanism to automatically learn the importance of each EEG channels in the seizure diagnosis procedure.
no code implementations • WS 2019 • Huiwei Zhou, Bizun Lei, Zhe Liu, Zhuang Liu
BioNLP 2019 proposes Question Answering (QA) task, which encourages the use of text mining technology to automatically judge whether a search result is an answer to the medical question.
2 code implementations • npj Computational Materials 2019 • Felipe Oviedo, Zekun Ren, Shijing Sun, Charles Settens, Zhe Liu, Noor Titan Putri Hartono, Savitha Ramasamy, Brian L. DeCost, Siyu I. P. Tian, Giuseppe Romano, Aaron Gilad Kusne, Tonio Buonassisi
We overcome the scarce data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data.
no code implementations • 30 Apr 2019 • Zhe Liu, Chuanzhe Suo, Shunbo Zhou, Huanshu Wei, Yingtian Liu, Hesheng Wang, Yun-hui Liu
Place recognition and loop-closure detection are main challenges in the localization, mapping and navigation tasks of self-driving vehicles.
no code implementations • 8 Jan 2019 • Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang
On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module.
2 code implementations • ICCV 2019 • Zhe Liu, Shunbo Zhou, Chuanzhe Suo, Yingtian Liu, Peng Yin, Hesheng Wang, Yun-hui Liu
Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments.
Ranked #5 on
3D Place Recognition
on CS-Campus3D
3 code implementations • 20 Nov 2018 • Felipe Oviedo, Zekun Ren, Shijing Sun, Charlie Settens, Zhe Liu, Noor Titan Putri Hartono, Ramasamy Savitha, Brian L. DeCost, Siyu I. P. Tian, Giuseppe Romano, Aaron Gilad Kusne, Tonio Buonassisi
X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials.
no code implementations • 12 Nov 2018 • Rama Akkiraju, Vibha Sinha, Anbang Xu, Jalal Mahmud, Pritam Gundecha, Zhe Liu, Xiaotong Liu, John Schumacher
For example, existing machine learning processes cannot address how to define business use cases for an AI application, how to convert business requirements from offering managers into data requirements for data scientists, and how to continuously improve AI applications in term of accuracy and fairness, and how to customize general purpose machine learning models with industry, domain, and use case specific data to make them more accurate for specific situations etc.
1 code implementation • 29 Oct 2018 • Tian Wang, Meina Qiao, Zhiwei Lin, Ce Li, Hichem Snoussi, Zhe Liu, Chang Choi
Security surveillance is critical to social harmony and people's peaceful life.
Ranked #3 on
Abnormal Event Detection In Video
on UBI-Fights
no code implementations • 17 Mar 2017 • Zhe Liu, Anbang Xu, Mengdi Zhang, Jalal Mahmud, Vibha Sinha
One problem that every presenter faces when delivering a public discourse is how to hold the listeners' attentions or to keep them involved.