LAMP

Fei’s paper Slimmable compressive autoencoders for practical neural image compression has been accepted for CVPR.

Also four CVPR workshop papers have been accepted:

• DANICE: Domain adaptation without forgetting in neural image compression,
• Continual learning in cross-modal retrieval,
• Ternary Feature Masks: zero-forgetting for task-incremental learning,
• Avalanche: an End-to-End Library for Continual Learning.