Search Results for author: Xudong Wang

Found 21 papers, 11 papers with code

SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference

no code implementations15 Mar 2023 Li Lyna Zhang, Xudong Wang, Jiahang Xu, Quanlu Zhang, Yujing Wang, Yuqing Yang, Ningxin Zheng, Ting Cao, Mao Yang

The combination of Neural Architecture Search (NAS) and quantization has proven successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN).

Neural Architecture Search Quantization

SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parametric Generator

no code implementations14 Sep 2022 Zesong Qiu, Yuwei Li, Dongming He, Qixuan Zhang, Longwen Zhang, Yinghao Zhang, Jingya Wang, Lan Xu, Xudong Wang, Yuyao Zhang, Jingyi Yu

Named after the fossils of one of the oldest known human ancestors, our LUCY dataset contains high-quality Computed Tomography (CT) scans of the complete human head before and after orthognathic surgeries, critical for evaluating surgery results.

Computed Tomography (CT)

Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech

no code implementations10 Aug 2022 Kaitao Song, Teng Wan, Bixia Wang, Huiqiang Jiang, Luna Qiu, Jiahang Xu, Liping Jiang, Qun Lou, Yuqing Yang, Dongsheng Li, Xudong Wang, Lili Qiu

Specifically, we first pre-train an encoder-decoder framework in an automatic speech recognition (ASR) objective by using speech-to-text dataset, and then fine-tune ASR encoder on the cleft palate dataset for hypernasality estimation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers

1 code implementation CVPR 2022 Tsung-Wei Ke, Jyh-Jing Hwang, Yunhui Guo, Xudong Wang, Stella X. Yu

We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features.

Unsupervised Semantic Segmentation

Debiased Learning from Naturally Imbalanced Pseudo-Labels

1 code implementation CVPR 2022 Xudong Wang, Zhirong Wu, Long Lian, Stella X. Yu

Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data.

Few-Shot Image Classification imbalanced classification +2

Hankel-structured Tensor Robust PCA for Multivariate Traffic Time Series Anomaly Detection

no code implementations8 Oct 2021 Xudong Wang, Luis Miranda-Moreno, Lijun Sun

We treat the raw data with anomalies as a multivariate time series matrix (location $\times$ time) and assume the denoised matrix has a low-rank structure.

Anomaly Detection Time Series Anomaly Detection

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

1 code implementation6 Oct 2021 Xudong Wang, Long Lian, Stella X. Yu

Intuitively, no matter what the downstream task is, instances to be labeled must be representative and diverse: The former would facilitate label propagation to unlabeled data, whereas the latter would ensure coverage of the entire dataset.

Active Learning Semi-Supervised Image Classification (Cold Start)

Source-Target Unified Knowledge Distillation for Memory-Efficient Federated Domain Adaptation on Edge Devices

no code implementations29 Sep 2021 Xiaochen Zhou, Yuchuan Tian, Xudong Wang

Moreover, to prevent the compact model from forgetting the knowledge of the source data during knowledge distillation, a collaborative knowledge distillation (Co-KD) method is developed to unify the source data on the server and the target data on the edge device to train the compact model.

Domain Adaptation Knowledge Distillation

FedNILM: Applying Federated Learning to NILM Applications at the Edge

no code implementations7 Jun 2021 Yu Zhang, Guoming Tang, Qianyi Huang, Yi Wang, Xudong Wang, Jiadong Lou

Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring.

Federated Learning Model Compression +3

Low-Rank Hankel Tensor Completion for Traffic Speed Estimation

1 code implementation21 May 2021 Xudong Wang, Yuankai Wu, Dingyi Zhuang, Lijun Sun

This paper studies the traffic state estimation (TSE) problem using sparse observations from mobile sensors.

Matrix Completion

Unsupervised Visual Attention and Invariance for Reinforcement Learning

no code implementations CVPR 2021 Xudong Wang, Long Lian, Stella X. Yu

Existing methods focus on training an RL policy that is universal to changing visual domains, whereas we focus on extracting visual foreground that is universal, feeding clean invariant vision to the RL policy learner.

Domain Generalization Keypoint Detection +2

A Communication Efficient Federated Kernel $k$-Means

no code implementations1 Jan 2021 Xiaochen Zhou, Xudong Wang

Theoretical analysis shows: 1) DSPGD with CEM converges with an $O(1/T)$ rate, where $T$ is the number of iterations; 2) the communication cost of DSPGD with CEM is unrelated to the number of data samples; 3) the clustering loss of the federated kernel $k$-means can approach that of the centralized kernel $k$-means.

Long-tailed Recognition by Routing Diverse Distribution-Aware Experts

2 code implementations ICLR 2021 Xudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu, Stella X. Yu

We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail.

Image Classification imbalanced classification +1

Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

1 code implementation25 Sep 2020 Xudong Wang, Stella X. Yu

The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules.

Instance Segmentation object-detection +2

Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination

2 code implementations CVPR 2021 Xudong Wang, Ziwei Liu, Stella X. Yu

Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets.

Contrastive Learning Semi-Supervised Image Classification +2

Structure-Feature based Graph Self-adaptive Pooling

1 code implementation30 Jan 2020 Liang Zhang, Xudong Wang, Hongsheng Li, Guangming Zhu, Peiyi Shen, Ping Li, Xiaoyuan Lu, Syed Afaq Ali Shah, Mohammed Bennamoun

To solve these problems mentioned above, we propose a novel graph self-adaptive pooling method with the following objectives: (1) to construct a reasonable pooled graph topology, structure and feature information of the graph are considered simultaneously, which provide additional veracity and objectivity in node selection; and (2) to make the pooled nodes contain sufficiently effective graph information, node feature information is aggregated before discarding the unimportant nodes; thus, the selected nodes contain information from neighbor nodes, which can enhance the use of features of the unselected nodes.

Graph Classification

Towards Universal Object Detection by Domain Attention

1 code implementation CVPR 2019 Xudong Wang, Zhaowei Cai, Dashan Gao, Nuno Vasconcelos

Experiments, on a newly established universal object detection benchmark of 11 diverse datasets, show that the proposed detector outperforms a bank of individual detectors, a multi-domain detector, and a baseline universal detector, with a 1. 3x parameter increase over a single-domain baseline detector.

object-detection Object Detection

Feature Space Transfer for Data Augmentation

no code implementations CVPR 2018 Bo Liu, Xudong Wang, Mandar Dixit, Roland Kwitt, Nuno Vasconcelos

A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose.

Data Augmentation Object Recognition +1

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