3 papers
cs.LG2024
Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning
Nidhin Harilal, Amit Kiran Rege, Reza Akbarian Bafghi +2
Self-supervised learning (SSL) has revolutionized learning from large-scale unlabeled datasets, yet the intrinsic relationship between pretraining data and the learned representati…
cs.CV2024
MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations
Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni +1
This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantl…
cs.CV2024
Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni +1
Artificial neural networks often suffer from catastrophic forgetting, where learning new concepts leads to a complete loss of previously acquired knowledge. We observe that this is…