2 papers
cs.LG2025
Memory-adaptive Depth-wise Heterogeneous Federated Learning
Kai Zhang, Yutong Dai, Hongyi Wang +3
Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devi…
cs.CV2024
MixMask: Revisiting Masking Strategy for Siamese ConvNets
Kirill Vishniakov, Eric Xing, Zhiqiang Shen
The recent progress in self-supervised learning has successfully combined Masked Image Modeling (MIM) with Siamese Networks, harnessing the strengths of both methodologies. Nonethe…