arXiv cs.CV
· Papers
Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
arXiv:2607.18625v1 Announce Type: new Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning t