Xialei Liu

is this you? claim profile

0 followers
Universitat Autònoma de Barcelona

Self-Training for Class-Incremental Semantic Segmentation

We study incremental learning for semantic segmentation where when learn...
12/06/2020 ∙ by Lu Yu, et al. ∙ 0 ∙ share

read it
Learning to Rank for Active Learning: A Listwise Approach

Active learning emerged as an alternative to alleviate the effort to lab...
07/31/2020 ∙ by Minghan Li, et al. ∙ 0 ∙ share

read it
Generative Feature Replay For Class-Incremental Learning

Humans are capable of learning new tasks without forgetting previous one...
04/20/2020 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

read it
Semantic Drift Compensation for Class-Incremental Learning

Class-incremental learning of deep networks sequentially increases the n...
04/01/2020 ∙ by Lu Yu, et al. ∙ 0 ∙ share

read it
Continual Universal Object Detection

Object detection has improved significantly in recent years on multiple ...
02/13/2020 ∙ by Xialei Liu, et al. ∙ 33 ∙ share

read it
Learning Metrics from Teachers: Compact Networks for Image Embedding

Metric learning networks are used to compute image embeddings, which are...
04/07/2019 ∙ by Lu Yu, et al. ∙ 0 ∙ share

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

For many applications the collection of labeled data is expensive labori...
02/17/2019 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

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

Previous works on sequential learning address the problem of forgetting ...
09/06/2018 ∙ by Chenshen Wu, et al. ∙ 12 ∙ share

read it
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

We propose a novel crowd counting approach that leverages abundantly ava...
03/08/2018 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

read it
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

In this paper we propose an approach to avoiding catastrophic forgetting...
02/08/2018 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

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

We propose a no-reference image quality assessment (NR-IQA) approach tha...
07/26/2017 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

read it

Xialei Liu

Featured Co-authors

Stefano Soatto

Kai Wang

Joost van de Weijer

Hao Yang

Antonio M. Lopez

Luis Herranz

Andrew D. Bagdanov

Yaxing Wang

Lu Yu

Avinash Ravichandran

Bogdan Raducanu

Self-Training for Class-Incremental Semantic Segmentation

Learning to Rank for Active Learning: A Listwise Approach

Generative Feature Replay For Class-Incremental Learning

Semantic Drift Compensation for Class-Incremental Learning

Continual Universal Object Detection

Learning Metrics from Teachers: Compact Networks for Image Embedding

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

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

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

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