Abstract: Federated learning is useful when predicting user preferences due to its ability to keep user data private. As such, certain data samples may be more useful than others. For instance, with a ...
We introduce DINOv2 SALAD, a Visual Place Recognition model that achieves state-of-the-art results on common benchmarks. We introduce two main contributions: Using a finetuned DINOv2 encoder to get ...
Abstract: As the scale of distributed training increases, it brings huge communication overhead in clusters. Some works try to reduce the communication cost through gradient compression or ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results