Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Jiahao Wang, Sucheng Ren, Guoyizhe Wei, Jieru Mei | Summary: Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much more severe in […]
Continue.. Mamba-R: Vision Mamba ALSO Needs Registers