Masked Autoencoder~(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data distributions different from the pre-training data, the semantically irrelevant pre-training information might result in negative transfer, impeding MAE's scalability. To address this issue, we propose a novel MAE-based pre-training paradigm, Mixture of Cluster-conditional Experts (MoCE), which can be trained once but provides customized pre-training models for diverse downstream tasks. Different from the mixture of experts (MoE), our MoCE trains each expert only with semantically relevant images by using cluster-conditional gates. Thus, each downstream task can be allocated to its customized model pre-trained with data most similar to the downstream data. Experiments on a collection of 11 downstream tasks show that MoCE outperforms the vanilla MAE by 2.45\% on average. It also obtains new state-of-the-art self-supervised learning results on detection and segmentation.
@article{arxiv.2402.05382,
title = {Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts},
author = {Zhili Liu and Kai Chen and Jianhua Han and Lanqing Hong and Hang Xu and Zhenguo Li and James T. Kwok},
journal= {arXiv preprint arXiv:2402.05382},
year = {2024}
}