Aoxue Li

Aoxue Li

Auto-generated profile, based on publicly available information

Aoxue Li

Peking University

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
4 September 2017
Verified
Book Chapter
Closed access
PDF file
JDJia Ding
Jia Ding
ALAoxue Li
Aoxue Li
ZHZhiqiang Hu
Zhiqiang Hu
LWLiwei Wang
Liwei Wang

1 June 2020
Verified
Conference Paper
Closed access
ALAoxue Li
Aoxue Li
WHWeiran Huang
Weiran Huang
XLXu Lan
Xu Lan
JFJiashi Feng
Jiashi Feng
ZLZhenguo Li
Zhenguo Li
LWLiwei Wang
Liwei Wang
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems. Specifically, we first develop a class-relevant additive margin loss, where semantic similarity between each pair of classes is considered to separate samples in the feature embedding space from similar classes. Further, we incorporate the semantic context among all classes in a sampled training task and develop a task-relevant additive margin loss to better distinguish samples from different classes. Our adaptive margin method can be easily extended to a more realistic generalized FSL setting. Extensive experiments demonstrate that the proposed method can boost the performance of current metric-based meta-learning approaches, under both the standard FSL and generalized FSL settings.

1 June 2019
Verified
Conference Paper
Closed access
ALAoxue Li
Aoxue Li
TLTiange Luo
Tiange Luo
ZLZhiwu Lu
Zhiwu Lu
TXTao Xiang
Tao Xiang
LWLiwei Wang
Liwei Wang
Recently, large-scale few-shot learning (FSL) becomes topical. It is discovered that, for a large-scale FSL problem with 1,000 classes in the source domain, a strong baseline emerges, that is, simply training a deep feature embedding model using the aggregated source classes and performing nearest neighbor (NN) search using the learned features on the target classes. The state-of-the-art large-scale FSL methods struggle to beat this baseline, indicating intrinsic limitations on scalability. To overcome the challenge, we propose a novel large-scale FSL model by learning transferable visual features with the class hierarchy which encodes the semantic relations between source and target classes. Extensive experiments show that the proposed model significantly outperforms not only the NN baseline but also the state-of-the-art alternatives. Furthermore, we show that the proposed model can be easily extended to the large-scale zero-shot learning (ZSL) problem and also achieves the state-of-the-art results.

17 April 2017 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
ALAoxue Li
Aoxue Li
ZLZhiwu Lu
Zhiwu Lu
LWLiwei Wang
Liwei Wang
TXTao Xiang
Tao Xiang
JWJi-Rong Wen
Ji-Rong Wen
Due to the rapid technological development of various sensors, a huge volume of high spatial resolution (HSR) image data can now be acquired. How to efficiently recognize the scenes from such HSR image data has become a critical task. Conventional approaches to remote sensing scene classification only utilize information from HSR images. Therefore, they always need a large amount of labeled data and cannot recognize the images from an unseen scene class without any visual sample in the labeled data. To overcome this drawback, we propose a novel approach for recognizing images from unseen scene classes, i.e., zero-shot scene classification (ZSSC). In this approach, we first use the well-known natural language process model, word2vec, to map names of seen/unseen scene classes to semantic vectors. A semantic-directed graph is then constructed over the semantic vectors for describing the relationships between unseen classes and seen classes. To transfer knowledge from the images in seen classes to those in unseen classes, we make an initial label prediction on test images by an unsupervised domain adaptation model. With the semantic-directed graph and initial prediction, a label-propagation algorithm is then developed for ZSSC. By leveraging the visual similarity among images from the same scene class, a label refinement approach based on sparse learning is used to suppress the noise in the zero-shot classification results. Experimental results show that the proposed approach significantly outperforms the state-of-the-art approaches in ZSSC.

1 October 2019
Verified
Conference Paper
Closed access
ALAoxue Li
Aoxue Li
TLTiange Luo
Tiange Luo
TXTao Xiang
Tao Xiang
WHWeiran Huang
Weiran Huang
LWLiwei Wang
Liwei Wang

1 March 2016 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
LZLibao Zhang
Libao Zhang
ALAoxue Li
Aoxue Li
ZZZhongjun Zhang
Zhongjun Zhang
KYKaina Yang
Kaina Yang
Extraction of residential areas plays an important role in remote sensing image processing. Extracted results can be applied to various scenarios, including disaster assessment, urban expansion, and environmental change research. Quality residential areas extracted from a remote sensing image must meet three requirements: well-defined boundaries, uniformly highlighted residential area, and no background redundancy in residential areas. Driven by these requirements, this study proposes a global and local saliency analysis model (GLSA) for the extraction of residential areas in high-spatial-resolution remote sensing images. In the proposed model, a global saliency map based on quaternion Fourier transform (QFT) and a global saliency map based on adaptive directional enhancement lifting wavelet transform (ADE-LWT) are generated along with a local saliency map, all of which are fused into a main saliency map based on complementarities. In order to analyze the correlation among spectrums in the remote sensing image, the phase spectrum information of QFT is used on the multispectral images for producing a global saliency map. To acquire the texture and edge features of different scales and orientations, the coefficients acquired by ADE-LWT are used to construct another global saliency map. To discard redundant backgrounds, the amplitude spectrum of the Fourier transform and the spatial relations among patches are introduced into the panchromatic image to generate the local saliency map. Experimental results indicate that the GLSA model can better define the boundaries of residential areas and achieve complete residential areas than current methods. Furthermore, the GLSA model can prevent redundant backgrounds in residential areas and thus acquire more accurate residential areas.