Search Results for author:
Found 6 papers, 4 papers with code
Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
To tackle these issues, we propose a continual self-supervised method, Adaptive Distribution Masked Autoencoders (ADMA), which enhances the extraction of target domain knowledge while mitigating the accumulation of distribution shifts.
Gradient-based Parameter Selection for Efficient Fine-Tuning
With the growing size of pre-trained models, full fine-tuning and storing all the parameters for various downstream tasks is costly and infeasible.
MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
Motivated by this, we propose Mixture of Sparse Adapters, or MoSA, as a novel Adapter Tuning method to fully unleash the potential of each parameter in the adapter.
Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction
The visual prompts have provided an efficient manner in addressing visual cross-domain problems.
Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
Neuromorphic spike data, an upcoming modality with high temporal resolution, has shown promising potential in real-world applications due to its inherent advantage to overcome high-velocity motion blur.
Boosting Certified $\ell_\infty$ Robustness with EMA Method and Ensemble Model
Moreover, we give the theoretical analysis of the ensemble method based on the $1$-Lipschitz property on the certified robustness, which ensures the effectiveness and stability of the algorithm.
