Kavli Affiliate: Zheng Zhu | First 5 Authors: Mengxuan Wu, Zekai Li, Zhiyuan Liang, Moyang Li, Xuanlei Zhao | Summary: Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy. For token redundancy, […]
Continue.. Dynamic Vision Mamba