6 papers
Self-Soupervision: Cooking Model Soups without Labels
Anthony Fuller, James R. Green, Evan Shelhamer
Model soups are strange and strangely effective combinations of parameters. They take a model (the stock), fine-tune it into multiple models (the ingredients), and then mix their p…
LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
Ali Salamatian, Anthony Fuller, Pritam Sarkar +3
Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are filled with redundancy, so…
Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers
Anthony Fuller, Yousef Yassin, Daniel G. Kyrollos +2
ViTs are general and accurate, and address many tasks, but ViTs are slow, and are not always practical when efficiency is key. Existing methods for faster ViTs design hybrid non-Vi…
LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
Anthony Fuller, Yousef Yassin, Junfeng Wen +4
Vision transformers are ever larger, more accurate, and more expensive to compute. The expense is even more extreme at high resolution as the number of tokens grows quadratically w…
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
Gabriel Tseng, Anthony Fuller, Marlena Reil +7
We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and m…
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate
Anthony Fuller, Daniel G. Kyrollos, Yousef Yassin +1
High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT…