4 citations · 5 across the 3 of their papers we have counts for
3 papers
cs.CV2024★ 1 cited
MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model
Rajat Sahay, Andreas Savakis
The emergence of foundation models, such as the Segment Anything Model (SAM), has sparked interest in Parameter-Efficient Fine-Tuning (PEFT) methods that tailor these large models…
cs.CV2024★ 4 cited
LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation
Navin Ranjan, Andreas Savakis
Vision transformers (ViTs) have demonstrated remarkable performance across various visual tasks. However, ViT models suffer from substantial computational and memory requirements,…
cs.CV2023
Unknown Sample Discovery for Source Free Open Set Domain Adaptation
Chowdhury Sadman Jahan, Andreas Savakis
Open Set Domain Adaptation (OSDA) aims to adapt a model trained on a source domain to a target domain that undergoes distribution shift and contains samples from novel classes outs…