62 citations · 117 across the 10 of their papers we have counts for
11 papers
Ti-MAE: Self-Supervised Masked Time Series Autoencoders
Zhe Li, Zhongwen Rao, Lujia Pan +2
Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have…
Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
Zhe Li, Man-Wai Mak
A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains.…
Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space
Zhe Li, Man-Wai Mak, Helen Mei-Ling Meng
The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs…
Masked Generative Distillation
Zhendong Yang, Zhe Li, Mingqi Shao +3
Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teac…
Focal and Global Knowledge Distillation for Detectors
Zhendong Yang, Zhe Li, Xiaohu Jiang +4
Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have fail…
CARLS: Cross-platform Asynchronous Representation Learning System
Chun-Ta Lu, Yun Zeng, Da-Cheng Juan +13
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge make…
ConTNet: Why not use convolution and transformer at the same time?
Haotian Yan, Zhe Li, Weijian Li +3
Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such a…
Class-Incremental Learning with Generative Classifiers
Gido M. van de Ven, Zhe Li, Andreas S. Tolias
Incrementally training deep neural networks to recognize new classes is a challenging problem. Most existing class-incremental learning methods store data or use generative replay,…
Temporal Action Segmentation from Timestamp Supervision
Zhe Li, Yazan Abu Farha, Juergen Gall
Temporal action segmentation approaches have been very successful recently. However, annotating videos with frame-wise labels to train such models is very expensive and time consum…
Long Short-Term Sample Distillation
Liang Jiang, Zujie Wen, Zhongping Liang +7
In the past decade, there has been substantial progress at training increasingly deep neural networks. Recent advances within the teacher--student training paradigm have establishe…
Learning From Brains How to Regularize Machines
Zhe Li, Wieland Brendel, Edgar Y. Walker +7
Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input…