Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models.
Longxiang TangZhuotao TianKai LiChunming HeHantao ZhouHengshuang ZhaoXiu LiJiaya JiaPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- learning process
- prior knowledge
- retrieval model
- supervised learning
- pre trained
- probabilistic model
- information retrieval
- document retrieval
- unsupervised learning
- reinforcement learning
- computer vision
- learning algorithm
- information extraction
- query expansion
- speech recognition
- relevance model
- smoothing methods
- neural network
- statistical language models