Lei Zhang

Lei Zhang

Auto-generated profile, based on publicly available information

Lei Zhang

Guangdong University of Petrochemical Technology

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 January 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
LZLei Zhang
Lei Zhang
LZLiyun Zuo
Liyun Zuo
YDYingjun Du
Yingjun Du
XZXiantong Zhen
Xiantong Zhen
Few-shot learning has recently generated increasing popularity in machine learning, which addresses the fundamental yet challenging problem of learning to adapt to new tasks with the limited data. In this paper, we propose a new probabilistic framework that learns to fast adapt with external memory. We model the classifier parameters as distributions that are inferred from the support set and directly applied to the query set for prediction. The model is optimized by formulating as a variational inference problem. The probabilistic modeling enables better handling prediction uncertainty due to the limited data. We impose a discriminative constraint on the feature representations by exploring the class structure, which can improve the classification performance. We further introduce a memory unit to store task-specific information extracted from the support set and used for the query set to achieve explicit adaption to individual tasks. By episodic training, the model learns to acquire the capability of adapting to specific tasks, which guarantees its performance on new related tasks. We conduct extensive experiments on widely-used benchmarks for few-shot recognition. Our method achieves new state-of-the-art performance and largely surpassing previous methods by large margins. The ablation study further demonstrates the effectiveness of the proposed discriminative learning and memory unit.

18 March 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
JSJiayi Shen
Jiayi Shen
ZXZehao Xiao
Zehao Xiao
XZXiantong Zhen
Xiantong Zhen
LZLei Zhang
Lei Zhang
Zero-shot Learning (ZSL) is a highly non-trivial task to generalize from seen to unseen classes. In this paper, we propose spherical zero-shot learning (SZSL) to address the major challenges in ZSL. By decoupling the similarity metric in the spherical embedding space into radius and angle, our SZSL can map classes to hyperspherical surfaces of different radiuses, which greatly increases its flexibility. Specifically, we introduce the spherical alignment on angles to spread classes as uniformly as possible to alleviate the hubness problem and simultaneously preserve the inter-class semantic structure to make the alignment more reasonable. We also introduce the spherical calibration with a minimum entropy based regularizer by adopting a larger radius for unseen classes than seen classes to reduce the prediction bias. Extensive experiments on five middle-scale benchmarks and large-scale ImageNet dataset demonstrate that the proposed approach consistently achieves superior performance for the traditional and generalized settings of ZSL.

6 May 2020 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
LZLei Zhang
Lei Zhang
XXXuezhi Xiang
Xuezhi Xiang

1 September 2020 in Pattern Recognition
Verified
Journal Article
Closed access
XZXiantong Zhen
Xiantong Zhen
MYMengyang Yu
Mengyang Yu
ZXZehao Xiao
Zehao Xiao
LZLei Zhang
Lei Zhang
LSLing Shao
Ling Shao

6 June 2023 in Soft Computing
Verified
Journal Article
Closed access
PDF file
JHJieguang He
Jieguang He
ZPZhiping Peng
Zhiping Peng
LZLei Zhang
Lei Zhang
LZLiyun Zuo
Liyun Zuo
DCDelong Cui
Delong Cui
QLQirui Li
Qirui Li

7 June 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
LZLiyun Zuo
Liyun Zuo
BWBaoyan Wang
Baoyan Wang
LZLei Zhang
Lei Zhang
JXJun Xu
Jun Xu
XZXiantong Zhen
Xiantong Zhen
Few-shot image classification aims to recognize unseen classes with few labeled samples. Existing meta-learning models learn good representations or model parameters to adapt to new tasks with a few training samples. However, when there a domain gap exists between training and test tasks, the learned ability often does not generalize well across domains, resulting in degraded performance on new tasks. In this paper, we propose variational neuron shifting to generate adapted feature representations for few-shot learning. We introduce a working memory module to store the shifted neurons from the support set, which will be accessed to generate adapted feature representations of query samples. Under the meta-learning paradigm, the model is learned to acquire the ability of adaptation with a single sample at meta-training time to further adapt itself to each single test sample at meta-test time. We formulate the adaptation process as a variational Bayesian inference problem, which incorporates the test sample as the condition into the generation of the model neuron shifting. We conduct extensive experiments on both within- and across-domain few-shot classification tasks. Good performance substantiates the effectiveness of the proposed variational neuron shifting, and thorough ablation studies demonstrate the benefit of each component in the proposed model.