347 citations · 610 across the 24 of their papers we have counts for
24 papers
Transsion TSUP's speech recognition system for ASRU 2023 MADASR Challenge
Xiaoxiao Li, Gaosheng Zhang, An Zhu +4
This paper presents a speech recognition system developed by the Transsion Speech Understanding Processing Team (TSUP) for the ASRU 2023 MADASR Challenge. The system focuses on ada…
Sparse Convolution for Approximate Sparse Instance
Xiaoxiao Li, Zhao Song, Guangyi Zhang
Computing the convolution of two vectors of dimension is one of the most important computational primitives in many fields. For the non-negative convolution scenari…
Biological Factor Regulatory Neural Network
Xinnan Dai, Caihua Shan, Jie Zheng +2
Genes are fundamental for analyzing biological systems and many recent works proposed to utilize gene expression for various biological tasks by deep learning models. Despite their…
Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
Yilin Yang, Kamil Adamczewski, Danica J. Sutherland +2
Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features it allows us to summa…
Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection
Ziteng Cui, Yingying Zhu, Lin Gu +5
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images. Most of these algorithms assume the…
Transcending XAI Algorithm Boundaries through End-User-Inspired Design
Weina Jin, Jianyu Fan, Diane Gromala +3
The boundaries of existing explainable artificial intelligence (XAI) algorithms are confined to problems grounded in technical users' demand for explainability. This research parad…
Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
Ruinan Jin, Xiaoxiao Li
Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research. Training generative adversarial neur…
Class Impression for Data-free Incremental Learning
Sana Ayromlou, Purang Abolmaesumi, Teresa Tsang +1
Standard deep learning-based classification approaches require collecting all samples from all classes in advance and are trained offline. This paradigm may not be practical in rea…
Dynamic Bank Learning for Semi-supervised Federated Image Diagnosis with Class Imbalance
Meirui Jiang, Hongzheng Yang, Xiaoxiao Li +3
Despite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsol…
Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Nan Lu, Zhao Wang, Xiaoxiao Li +3
Supervised federated learning (FL) enables multiple clients to share the trained model without sharing their labeled data. However, potential clients might even be reluctant to lab…
RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images
Ziteng Cui, Yingying Zhu, Lin Gu +5
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assum…
Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
Yifei Huang, Xiaoxiao Li, Lijin Yang +6
The human gaze is a cost-efficient physiological data that reveals human underlying attentional patterns. The selective attention mechanism helps the cognition system focus on task…
FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
Liang Peng, Nan Wang, Nicha Dvornek +2
Graph Convolutional Neural Networks (GCNs) are widely used for graph analysis. Specifically, in medical applications, GCNs can be used for disease prediction on a population graph,…
SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition
Li Fu, Xiaoxiao Li, Runyu Wang +5
End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervisio…
EMA: Auditing Data Removal from Trained Models
Yangsibo Huang, Xiaoxiao Li, Kai Li
Data auditing is a process to verify whether certain data have been removed from a trained model. A recently proposed method (Liu et al. 20) uses Kolmogorov-Smirnov (KS) distance f…
BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
Hejie Cui, Wei Dai, Yanqiao Zhu +3
Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are…
One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images
Weina Jin, Xiaoxiao Li, Ghassan Hamarneh
Being able to explain the prediction to clinical end-users is a necessity to leverage the power of AI models for clinical decision support. For medical images, saliency maps are th…
Subgraph Federated Learning with Missing Neighbor Generation
Ke Zhang, Carl Yang, Xiaoxiao Li +2
Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions. As graphs are getting bigger and b…
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis
Baihe Huang, Xiaoxiao Li, Zhao Song +1
Federated Learning (FL) is an emerging learning scheme that allows different distributed clients to train deep neural networks together without data sharing. Neural networks have b…
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang +2
The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improv…
MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
Xiaoxiao Li, Yangsibo Huang, Binghui Peng +2
To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data…
Incremental Learning for End-to-End Automatic Speech Recognition
Li Fu, Xiaoxiao Li, Libo Zi +4
In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintainin…
Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition
Li Fu, Xiaoxiao Li, Libo Zi
Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Ma…
Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification
Xiaoxiao Li, Joao Saude
Real data collected from different applications that have additional topological structures and connection information are amenable to be represented as a weighted graph. Consideri…