Tengfei Zhang

Tengfei Zhang

Auto-generated profile, based on publicly available information

Tengfei Zhang

Inspur (Beijing) Electronic Information Industry Co., Ltd Beijing P.R.China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
22 February 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
KFKun Fu
Kun Fu
TZTengfei Zhang
Tengfei Zhang
YZYue Zhang
Yue Zhang
ZWZhirui Wang
Zhirui Wang
XSXian Sun
Xian Sun
The state-of-the-art deep neural networks have made a great breakthrough in remote sensing image classification. However, the heavy dependence on large-scale data sets limits the application of the deep learning to synthetic aperture radar (SAR) automatic target recognition (ATR) field where the target sample set is generally small. In this work, a metalearning framework named MSAR, consisting of a metalearner and a base-learner, is proposed to solve the sample restriction problem, which can learn a good initialization as well as a proper update strategy. After training, MSAR can implement fast adaptation with a few training images on new tasks. To the best of our knowledge, this is the first study to solve a few-shot SAR target classification via metalearning. In particular, the few-task problem is defined by analyzing the effect of available training classes on the performance of metalearning models. In order to reduce the metalearning difficulties caused by the few-task problem, three transfer-learning methods are employed, which can leverage the prior knowledge from the pretraining phase. Besides, we design a hard task mining method for effective metalearning. Based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, a specialized data set named NIST-SAR is devised to train and evaluate the proposed method. The experiments on NIST-SAR have shown that the proposed method yields better performances with the largest absolute improvements of 1.7% and 2.3% for 1-shot and 5-shot, respectively, over the next best, which indicates that the proposed method is promising and metalearning is a feasible solution for few-shot SAR ATR.

12 June 2019 in IEEE Access
Verified
Journal Article
Open access
KFKun Fu
Kun Fu
TZTengfei Zhang
Tengfei Zhang
YZYue Zhang
Yue Zhang
MYMenglong Yan
Menglong Yan
ZCZhonghan Chang
Zhonghan Chang
XSXian Sun
Xian Sun
State-of-the-art object detection frameworks require the training on large-scale datasets, which is the crux of the present dilemma: overfitting or degrading performance with insufficient samples and time-consuming training process. On the basis of meta-learning, this paper proposes a generalized Few-Shot Detection (FSD) framework to overcome the above drawbacks of the current advances in object detection. The proposed framework consists of a meta-learner and an object detector. It can learn the general knowledge and proper fast adaptation strategies across many tasks. The meta-learner can teach the detector how to learn from few examples in just one updating step. Here, the object detector can be any supervised learning detection models in theory. Specifically, the proposed FSD framework employs Single-Shot MultiBox Detector (SSD) as the object detector in this work, thus called Meta-SSD. Besides, a novel benchmark is constructed from Pascal VOC dataset for training and evaluation of meta-learning FSD. Experiments show that Meta-SSD yields a promising result for FSD. Furthermore, the properties of Meta-SSD is analyzed. This work can serve as a strong baseline and provide some inspiration for meta-learning FSD.

14 November 2019 in IEEE Access
Verified
Journal Article
Open access
ZCZhiying Cao
Zhiying Cao
TZTengfei Zhang
Tengfei Zhang
WDWenhui Diao
Wenhui Diao
YZYue Zhang
Yue Zhang
XLXiaode Lyu
Xiaode Lyu
XSXian Sun
Xian Sun
Semantic segmentation performs pixel-wise classification for given images, which can be widely used in autonomous driving, robotics, medical diagnostics and etc. The recent advanced approaches have witnessed rapid progress in semantic segmentation. However, these supervised learning based methods rely heavily on large-scale datasets to acquire strong generalizing ability, such that they are coupled with some constraints. Firstly, human annotation of pixel-level segmentation masks is laborious and time-consuming, which causes relatively expensive training data and make it hard to deal with urgent tasks in dynamic environment. Secondly, the outstanding performance of the above data-hungry methods will decrease with few available training examples. In order to overcome the limitations of the supervised learning semantic segmentation methods, this paper proposes a generalized meta-learning framework, named Meta-Seg. It consists of a meta-learner and a base-learner. Specifically, the meta-learner learns a good initialization and a parameter update strategy from a distribution of few-shot semantic segmentation tasks. The base-learner can be any semantic segmentation models theoretically and can implement fast adaptation (that is updating parameters with few iterations) under the guidance of the meta-learner. In this work, the successful semantic segmentation model FCN8s is integrated into Meta-Seg. Experiments on the famous few-shot semantic segmentation dataset PASCAL5i prove Meta-Seg is a promising framework for few-shot semantic segmentation. Besides, this method can provide with reference for the relevant researches of meta-learning semantic segmentation.

4 November 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WLWei Liang
Wei Liang
TZTengfei Zhang
Tengfei Zhang
WDWenhui Diao
Wenhui Diao
XSXian Sun
Xian Sun
ZLzhao liangjin
zhao liangjin
YWYirong Wu
Yirong Wu
Synthetic Aperture Radar (SAR) target classification is an important branch of SAR image interpretation. The deep learning based SAR target classification algorithms have made remarkable achievements. But the acquisition and annotation of SAR target images are time-consuming and laborious, and it is difficult to obtain sufficient training data in many cases. The insufficient training data can make deep learning based models suffering from over-fitting, which will severely limit their wide application in SAR target classification. Motivated by the above problem, this paper employs transfer-learning to transfer the prior knowledge learned from a simulated SAR dataset to a real SAR dataset. To overcome the sample restriction problem caused by the poor feature discriminability for real SAR data. A simple and effective sample spectral regularization method is proposed, which can regularize the singular values of each SAR image feature to improve the feature discriminability. Based on the proposed regularization method, we design a transfer-learning pipeline to leverage the simulated SAR data as well as acquire better feature discriminability. The experimental results indicate that the proposed method is feasible for the sample restriction problem in SAR target classification. Furthermore, the proposed method can improve the classification accuracy when relatively sufficient training data is available, and it can be plugged into any convolutional neural network (CNN) based SAR classification models.

1 April 2017
Verified
Conference Paper
Closed access
TZTengfei Zhang
Tengfei Zhang
DLDan Liu
Dan Liu
Dong YueDong Yue
Dong Yue
Short-term load in power system is nonlinear and non-stationary. To cope with the problem that the training error of neural network prediction model is increased while the generalization ability is reduced caused by the large input fluctuation, the rough neurons with upper and lower inputs are introduced into the radial basis function (RBF) neural networks, a power system short-term load forecasting model based on rough RBF neural networks is presented. The genetic algorithm is used to optimize related parameters of rough neural networks to find the best parameters in the global. The simulation results show that the proposed method can effectively improve the prediction accuracy of the power system short-term load.

3 April 2020 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
姜闫姜桥 闫
姜桥 闫
YZYue Zhang
Yue Zhang
ZCZhonghan Chang
Zhonghan Chang
TZTengfei Zhang
Tengfei Zhang
MYMenglong Yan
Menglong Yan
XSXian Sun
Xian Sun
Feature pyramid is the mainstream method for multi-scale object detection. In most detectors with feature pyramid, each proposal is predicted based on feature grids pooled from only one feature level, which is assigned heuristically. Recent studies report that the feature representation extracted using this method is sub-optimal, since they ignore the valid information exists on other unselected layers of the feature pyramid. To address this issue, researchers present to fuse valid information across all feature levels. However, these methods can be further improved: the feature fusion strategies, which use common operation (element-wise max or sum) in most detectors, should be replaced by a more flexible way. In this work, a novel method called feature adaptive selection subnetwork (FAS-Net) is proposed to construct effective features for detecting objects of different scales. Particularly, its adaption consists of two level: global attention and local adaptive selection. First, we model the global context of each feature map with global attention based feature selection module (GAFSM), which can strengthen the effective features across each layer adaptively. Then we extract the features of each region of interest (RoI) on the entire feature pyramid to construct a RoI feature pyramid. Finally, the RoI feature pyramid is sent to the feature adaptive selection module (FASM) to integrate the strengthened features according to the input adaptively. Our FAS-Net can be easily extended to other two-stage object detectors with feature pyramid, and supports to analyze the importance of different feature levels for multi-scale objects quantitatively. Besides, FAS-Net can also be further applied to instance segmentation task and get consistent improvements. Experiments on PASCAL07/12 and MSCOCO17 demonstrate the effectiveness and generalization of the proposed method.