2.3k citations · 2.3k across the 3 of their papers we have counts for
3 papers
RADIO1D: Elastic Representations for Condensed Vision Modeling
Greg Heinrich, Mike Ranzinger, Collin McCarthy +6
This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features. Analyzing fine-tuned vision encoders, we find that representat…
Fully convolutional Siamese neural networks for buildings damage assessment from satellite images
Eugene Khvedchenya, Tatiana Gabruseva
Damage assessment after natural disasters is needed to distribute aid and forces to recovery from damage dealt optimally. This process involves acquiring satellite imagery for the…
Albumentations: fast and flexible image augmentations
Alexander Buslaev, Alex Parinov, Eugene Khvedchenya +2
Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve output labe…