568 citations · 2.2k across the 54 of their papers we have counts for
57 papers
More Data Cannot Break a Symmetry: Identifiability by Design
Jing Xu, Christopher Kanan
Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus geometry bounds what any such…
Virchow: A Million-Slide Digital Pathology Foundation Model
Eugene Vorontsov, Alican Bozkurt, Adam Casson +28
The use of artificial intelligence to enable precision medicine and decision support systems through the analysis of pathology images has the potential to revolutionize the diagnos…
GRASP: A Rehearsal Policy for Efficient Online Continual Learning
Md Yousuf Harun, Jhair Gallardo, Junyu Chen +1
Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-statio…
Understanding the Benefits of Image Augmentations
Matthew Iceland, Christopher Kanan
Image Augmentations are widely used to reduce overfitting in neural networks. However, the explainability of their benefits largely remains a mystery. We study which layers of resi…
Overcoming the Stability Gap in Continual Learning
Md Yousuf Harun, Christopher Kanan
Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the D…
How Efficient Are Today's Continual Learning Algorithms?
Md Yousuf Harun, Jhair Gallardo, Tyler L. Hayes +1
Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forg…