93 citations · 140 across the 13 of their papers we have counts for
13 papers
RCT: Resource Constrained Training for Edge AI
Tian Huang, Tao Luo, Ming Yan +2
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devi…
Natural Language Video Localization: A Revisit in Span-based Question Answering Framework
Hao Zhang, Aixin Sun, Wei Jing +3
Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a text query. Existing approaches mainly solve th…
Deep N-ary Error Correcting Output Codes
Hao Zhang, Joey Tianyi Zhou, Tianying Wang +2
Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. To this end, data-independent ensemble metho…
EDCompress: Energy-Aware Model Compression for Dataflows
Zhehui Wang, Tao Luo, Joey Tianyi Zhou +1
Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compressi…
Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning
Renuga Kanagavelu, Zengxiang Li, Juniarto Samsudin +7
Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where…
Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
Shaohua Li, Xiuchao Sui, Jie Fu +2
Convolutional Neural Networks (CNNs) are known to be brittle under various image transformations, including rotations, scalings, and changes of lighting conditions. We observe that…
Privacy-preserving Weighted Federated Learning within Oracle-Aided MPC Framework
Huafei Zhu, Zengxiang Li, Mervyn Cheah +1
This paper studies privacy-preserving weighted federated learning within the oracle-aided multi-party computation (MPC) framework. The contribution of this paper mainly comprises t…
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
Jiawei Du, Hanshu Yan, Vincent Y. F. Tan +3
It has been shown that the majority of existing adversarial defense methods achieve robustness at the cost of sacrificing prediction accuracy. The undesirable severe drop in accura…
Multi-Instance Multi-Scale CNN for Medical Image Classification
Shaohua Li, Yong Liu, Xiuchao Sui +4
Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs)…
Multi-Modal Hybrid Deep Neural Network for Speech Enhancement
Zhenzhou Wu, Sunil Sivadas, Yong Kiam Tan +2
Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corru…
Transfer Hashing with Privileged Information
Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan +3
Most existing learning to hash methods assume that there are sufficient data, either labeled or unlabeled, on the domain of interest (i.e., the target domain) for training. However…
Simple and Efficient Learning using Privileged Information
Xinxing Xu, Joey Tianyi Zhou, IvorW. Tsang +3
The Support Vector Machine using Privileged Information (SVM+) has been proposed to train a classifier to utilize the additional privileged information that is only available in th…
Optimizing the MapReduce Framework on Intel Xeon Phi Coprocessor
Mian Lu, Lei Zhang, Huynh Phung Huynh +5
With the ease-of-programming, flexibility and yet efficiency, MapReduce has become one of the most popular frameworks for building big-data applications. MapReduce was originally d…