Dr. Xialei Liu @ Research Associate

Recent News

Research Associate at University of Edinburgh Now (Updated on 2020-09-20).

Research Assistant at Computer Vision Center from 2019-12-17 to 2020-09-16 (10 months).

1 paper is accepted at CVPR 2020, Seattle, WA, USA.

1 paper is available at arXiv (Continual Universal Object Detection). - Link

Amazon applied scientist intern (from May to September, 4 months, 2019), Seattle, WA, USA.

1 paper is accepted at CVPR 2019, Long Beach, CA, USA.

1 paper is accepted at TPAMI.

Won the third prize of Baidu Star Development Competition 2018, Beijing, China.

1 paper is accepted by NIPS 2018, Montreal, Canada.

1 paper (Oral presentation) is accepted by ICPR 2018, Beijing, China.

1 paper is accepted by CVPR 2018, Utah, USA.

Presented the Real Time Crowd Counting Demo in MWC 2018, Barcelona, Spain - Media Coverage

Invited Talk: Lifelong Learning Seminar - Link

Presented the RankIQA paper in ICCV 2017, Venice, Italy.

Attended the international conference NIPS 2016, Barcelona, Spain.

Conferences

Learning Metrics from Teachers: Compact Networks for Image Embedding

Authors: Lu Yu, Vacit Oguz Yazici, Xialei Liu, Joost van de Weijer, Yongmei Cheng, Arnau Ramisa

International Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Find out more

Memory Replay GANs: learning to generate images from new categories without forgetting

Authors: Chenshen Wu, Luis Herranz, Xialei Liu, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu

Thirty-second Conference on Neural Information Processing Systems (NIPS), 2018

Find out more

Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

Authors: Xialei Liu, Marc Masana, Luis Herranz, Joost Van de Weijer, Antonio M. Lopez, Andrew D. Bagdanov

International Conference on Pattern Recognition (ICPR), 2018

Find out more

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Authors: Xialei Liu, Joost van de Weijer, Andrew D Bagdanov

International Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Find out more

RankIQA: Learning from Rankings for No-reference Image Quality Assessment

Authors: Xialei Liu, Joost van de Weijer, Andrew D Bagdanov

International Conference on Computer Vision (ICCV), 2017

Find out more

Journals

Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank

Authors: Xialei Liu, Joost van de Weijer, Andrew D Bagdanov

Transactions on Pattern Analysis and Machine Intelligence, 2019

Find out more

Projects

Master Thesis:

Learning from rankings for no-reference image quality assessment by Siamese Network

Advisors: Joost van de Weijer and Andrew D. Bagdanov

Find out more

PhD Thesis:

Visual recognition in the wild: learning from rankings in small domains and continual learning in new domains

Advisors: Joost van de Weijer and Andrew D. Bagdanov

Abstract: Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition application, such as image classification, detection and segmentation. In this thesis we address two limitations of CNNs. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Another limitation is that training CNNs in a continual learning setting is still an open research question. Catastrophic forgetting is very likely when adapting trained models to new environments or new tasks. Therefore, in this thesis, we aim to improve CNNs for applications with limited data and to adapt CNNs continually to new tasks. Self-supervised learning leverages unlabelled data by introducing an auxiliary task for which data is abundantly available. In the first part of the thesis, we show how rankings can be used as a proxy self-supervised task for regression problems. Then we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch net- work architecture. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning. We then apply our framework on two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both, we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results. We further show that active learning using rankings can reduce labeling effort by up to 50% for both IQA and crowd counting. In the second part of the thesis, we propose two approaches to avoiding catas- trophic forgetting in sequential task learning scenarios. The first approach is derived from Elastic Weight Consolidation, which uses a diagonal Fisher Information Matrix (FIM) to measure the importance of the parameters of the network. However the diagonal assumption is unrealistic. Therefore, we approximately diagonalize the FIM using a set of factorized rotation parameters. This leads to significantly better performance on continual learning of sequential tasks. For the second approach, we show that forgetting manifests differently at different layers in the network and iiipropose a hybrid approach where distillation is used in the feature extractor and replay in the classifier via feature generation. Our method addresses the limitations of generative image replay and probability distillation (i.e. learning without forget- ting) and can naturally aggregate new tasks in a single, well-calibrated classifier. Experiments confirm that our proposed approach outperforms the baselines and some start-of-the-art methods.

Find out more

Experience

Support researcher - Computer Vision Center (Sep 2015 - Now)

Collaborate within the Learning and Machine Perception (LAMP) groups at different research projects.

Scholarship holder - China Scholarship Council (Sep 2015 - Sep 2019)

PhD scholarship.

Journal reviewer

Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), IEEE Transactions on Image Processing (T-IP), Pattern Recognition (PR), IEEE Transactions on Multimedia (T-MM), Machine Vision and Applications.

Conference reviewer

ECCV'18, ACCV'18, WACV'19, BMVC'19, CVPR'19, ICCV'19, ACM MM Asia'19, CVPR'20, ECCV'20, BMVC'20, NeurIPS'20, ICPR'20, AAAI'21, ICLR'21, CVPR'21, ICML'21.

Bio

I received my B.Sc. and M.Sc. degrees in Information Engineering and Control Engineering from the Northwestern Polytechnic university (NWPU), China in 2013 and 2016, respectively. I received my second M.Sc. degree and PhD degree in Computer Vision from the Universitat Autònoma de Barcelona (UAB), Barcelona in 2016 and 2019, respectively. Currently, I am a Research Associate at University of Edinburgh. My main research interests include Deep Neural Networks, Object Detection, Image Quality Assessment, Crowd Counting, GANs and Lifelong Learning.

My Curriculum-Vitae

Computer Vision Center
Edifici O, Universitat Autònoma de Barcelona
08193, Bellaterra, Barcelona, Catalunya

Phone:+34 93 581 1828
Email:xialei <at> cvc.uab.es
Website:http://www.cvc.uab.es/LAMP/

Skills

My background on Information and Control Engineering and Computer Science provides a good knowledge to understand novel research topics.