2024/06/11 by Sucheng Ren, Xianhang Li, Ren, Sucheng +21 · 2 citations
Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Spatial Cognition and Navigation
paper · pdf · doi:10.48550/arxiv.2406.07537
openalex publication_date 2024/06/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive pretraining, a direction not previously explored. Efficiency-wise, the autoregressive nature can well capitalize on the Mamba's unidirectional recurrent structure, enabling faster overall training speed compared to other training strategies like mask modeling. Performance-wise, autoregressive pretraining equips the Mamba architecture with markedly higher accuracy over its supervised-trained counterparts and, more importantly, successfully unlocks its scaling potential to large and even huge model sizes. For example, with autoregressive pretraining, a base-size Mamba attains 83.2% ImageNet accuracy, outperforming its supervised counterpart by 2.0%; our huge-size Mamba, the largest Vision Mamba to date, attains 85.0% ImageNet accuracy (85.5% when finetuned with 384×384 inputs), notably surpassing all other Mamba variants in vision. The code is available at \urlhttps://github.com/OliverRensu/ARM.