FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models 事件

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models arXiv:2605.28347v1 Announce Type: new Abstract: Multi-Label Recognition (MLR) based on Vision-Language Models (VLMs) aims to leverage their pre-trained knowledge to better adapt complex recognition scenarios, thereby enhancing model robustness. However, for realistic decentralized applications requiring federated learning, adapting VLMs to each client that possesses private and heterogeneous data can cause the model to overfi