Search Results for author:
Found 4 papers, 2 papers with code
Maintain Plasticity in Long-timescale Continual Test-time Adaptation
Based on this correlation, we propose a simple yet effective policy, Adaptive Shrink-Restore (ASR), towards preserving the model's plasticity.
Efficient Transfer Learning for Video-language Foundation Models
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks.
Backpropagation-free Network for 3D Test-time Adaptation
Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
Continual Test-time Domain Adaptation via Dynamic Sample Selection
DSS consists of dynamic thresholding, positive learning, and negative learning processes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
