Search Results for author:
Found 3 papers, 1 papers with code
Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration
Meanwhile, our RebQ leverages extensive multi-modal knowledge from pre-trained LMMs to reconstruct the data of missing modality.
Efficient Meta-Learning for Continual Learning with Taylor Expansion Approximation
However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available.
TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval
Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the text with fine-grained features which relies on complicated model designs, or modeling fine-grained interaction via cross-attention upon visual and textual tokens which suffers from inferior efficiency.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
