VCMamba reports that using convolutional feed-forward blocks for the first three stages followed by multi-directional Mamba blocks in the final stage yields 82.6% ImageNet-1K and 47.1 ADE20K mIoU at 31.5M parameters, beating PlainMamba-L3, ViG-B, and EfficientFormer-L7 at fewer parameters.
Deep residual learning for image recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation
VCMamba reports that using convolutional feed-forward blocks for the first three stages followed by multi-directional Mamba blocks in the final stage yields 82.6% ImageNet-1K and 47.1 ADE20K mIoU at 31.5M parameters, beating PlainMamba-L3, ViG-B, and EfficientFormer-L7 at fewer parameters.