Abstract: Conventional federated learning (FL) assumes the homogeneity of models, necessitating clients to expose their model parameters to enhance the performance of the server model. However, this ...
Abstract: Multi-modal- image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results