research
∙
06/13/2023
One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
We present Generalized LoRA (GLoRA), an advanced approach for universal ...
share
research
∙
01/31/2023
Patch Gradient Descent: Training Neural Networks on Very Large Images
Traditional CNN models are trained and tested on relatively low resoluti...
research
∙
11/24/2022
On designing light-weight object trackers through network pruning: Use CNNs or transformers?
Object trackers deployed on low-power devices need to be light-weight, h...
research
∙
06/03/2022
Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning
Gradient based meta-learning methods are prone to overfit on the meta-tr...
research
∙
01/03/2022
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
This paper explores the feasibility of finding an optimal sub-model from...
research
∙
08/09/2021
Transfer Learning Gaussian Anomaly Detection by Fine-Tuning Representations
Current state-of-the-art Anomaly Detection (AD) methods exploit the powe...
research
∙
02/14/2021
ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
Structured pruning methods are among the effective strategies for extrac...
research
∙
01/14/2021
Rescaling CNN through Learnable Repetition of Network Parameters
Deeper and wider CNNs are known to provide improved performance for deep...
research
∙
03/23/2020