DeMansia: Mamba Never Forgets Any Tokens
This work addresses efficiency issues in image classification for AI researchers, though it appears incremental as it builds on existing models like Mamba and Vision Mamba.
The paper tackles the computational challenges of transformers in handling long sequences by proposing DeMansia, an architecture that integrates state space models with token labeling for image classification, showing effectiveness in benchmarks compared to contemporary models.
This paper examines the mathematical foundations of transformer architectures, highlighting their limitations particularly in handling long sequences. We explore prerequisite models such as Mamba, Vision Mamba (ViM), and LV-ViT that pave the way for our proposed architecture, DeMansia. DeMansia integrates state space models with token labeling techniques to enhance performance in image classification tasks, efficiently addressing the computational challenges posed by traditional transformers. The architecture, benchmark, and comparisons with contemporary models demonstrate DeMansia's effectiveness. The implementation of this paper is available on GitHub at https://github.com/catalpaaa/DeMansia