ECCV 2024 中与mamba相关的文献分享

ECCV（European Conference on Computer Vision，欧洲计算机视觉会议）是计算机视觉领域的顶级会议。ECCV 2024 于9月29日-10月4日在意大利米兰举行。

ECCV2024公布了录用论文名单，共2395篇，录用率18%。多位学者及团队在图像编辑、生成等领域提出新算法或模型，并被ECCV接收。

Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion  （ECCV 2024 最佳论文奖)

Famba-V：具有跨层令牌融合的快速视觉 Mamba

Abstract: Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models. The key idea of Famba-V is to identify and fuse similar tokens across different Vim layers based on a suit of cross-layer strategies instead of simply applying token fusion uniformly across all the layers that existing works propose. We evaluate the performance of Famba-V on CIFAR-100. Our results show that Famba-V is able to enhance the training efficiency of Vim models by reducing both training time and peak memory usage during training. Moreover, the proposed cross-layer strategies allow Famba-V to deliver superior accuracy-efficiency trade-offs. These results all together demonstrate Famba-V as a promising efficiency enhancement technique for Vim models. 

地址：arXiv:2409.09808 

VideoMamba: Spatio-Temporal Selective State Space Model

VideoMamba：时空选择性状态空间模型 

Abstract: