Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Universal Representations: A Unified Look at Multiple Task and Domain Learning



Wei-Hong Li , Xialei Liu , Hakan Bilen

* Multi-task Learning, Multi-domain Learning, Cross-domain Few-shot Learning, Universal Representation Learning, Balanced Optimization, Dense Prediction, Code will be available at https://github.com/VICO-UoE/UniversalRepresentations. arXiv admin note: text overlap with arXiv:2103.13841 

   Access Paper or Ask Questions

Representation Compensation Networks for Continual Semantic Segmentation



Chang-Bin Zhang , Jia-Wen Xiao , Xialei Liu , Ying-Cong Chen , Ming-Ming Cheng

* Accepted by CVPR 2022 

   Access Paper or Ask Questions

Learning Multiple Dense Prediction Tasks from Partially Annotated Data



Wei-Hong Li , Xialei Liu , Hakan Bilen

* Multi-task Partially-supervised Learning 

   Access Paper or Ask Questions

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition



Kai Wang , Xialei Liu , Andy Bagdanov , Luis Herranz , Shangling Jui , Joost van de Weijer


   Access Paper or Ask Questions

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification



Kai Wang , Xialei Liu , Luis Herranz , Joost van de Weijer

* accepted in BMVC 2021 

   Access Paper or Ask Questions

Improving Task Adaptation for Cross-domain Few-shot Learning



Wei-Hong Li , Xialei Liu , Hakan Bilen

* Code will be available at https://github.com/VICO-UoE/URL 

   Access Paper or Ask Questions

Universal Representation Learning from Multiple Domains for Few-shot Classification



Wei-Hong Li , Xialei Liu , Hakan Bilen

* Code will be available at https://github.com/VICO-UoE/URL 

   Access Paper or Ask Questions

Self-Training for Class-Incremental Semantic Segmentation



Lu Yu , Xialei Liu , Joost van de Weijer

* Code will be available 

   Access Paper or Ask Questions

Class-incremental learning: survey and performance evaluation



Marc Masana , Xialei Liu , Bartlomiej Twardowski , Mikel Menta , Andrew D. Bagdanov , Joost van de Weijer


   Access Paper or Ask Questions

1
2
>>