AAAI 2025 中最新的关于Mamba的研究

AAAI（Association for the Advancement of Artificial Intelligence，人工智能促进协会年会）是人工智能领域的顶级会议之一，将于2025 年 2 月 25 日至 3 月 4 日 在宾夕法尼亚州费城举办。

12月9日已经公布最终收录文献，在此博主汇总了其中与mamba有关的文献，供大家学习。

 SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks

SparX：分层视觉 Mamba 和 Transformer 网络的稀疏跨层连接机制

Abstract: Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with linear-time computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid development of Mamba-based vision models, resulting in promising results in visual recognition tasks. However, such models are not capable of distilling features across layers through feature aggregation, interaction, and selection. Moreover, existing cross-layer feature aggregation methods designed for CNNs or ViTs are not practical in Mamba-based models due to high computational costs. Therefore, this paper aims to introduce an efficient cross-layer feature aggregation mechanism for vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX to effectively improve cross-layer feature interaction and reuse. Specifically, we build two different types of network layers: ganglion layers and normal layers. The former has higher connectivity and complexity, enabling multi-layer feature aggregation and interaction in an input-dependent manner. In contrast, the latter has lower connectivity and complexity. By interleaving these two types of layers, we design a new family of vision backbone networks with sparsely cross-connected layers, achieving an excellent trade-off among model size, computational cost, memory cost, and accuracy in comparison to its counterparts. For instance, with fewer parameters, SparX-Mamba-T improves the top-1 accuracy of VMamba-T from 82.5\% to 83.5\%, while SparX-Swin-T achieves a 1.3\% increase in top-1 accuracy compared to Swin-T. Extensive experimental results demonstrate that our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
地址：arXiv:2409.09649

PoseMamba: Monocular 3D Human Pose Estimation with