Johannes Brandstetter
Johannes Brandstetter
Home
News
NXAI
Research
Publications
Experience
Teaching
Open Positions
Light
Dark
Automatic
Pretraining
Vision-LSTM -- xLSTM as Generic Vision Backbone
We introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision.
Mim-refiner -- A contrastive learning boost from intermediate pre-trained representations
We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models.
Cite
×