
Vision-RWKV is a model adapted from the RWKV model, designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities, offering a more efficient alternative for visual perception tasks.


coremsg

vision-rwkv-efficient-and-scalable-visual-perception-with-linear-attention-mechanism


Vision-RWKV: Efficient and Scalable Visual Perception with Linear Attention Mechanism


title_rewrite


The paper proposes a Single-Head Vision Transformer (SHViT) that achieves state-of-the-art speed-accuracy tradeoff on various devices by addressing computational redundancies in both macro (spatial) and micro (channel) design.


single-head-vision-transformer-with-memory-efficient-macro-and-micro-design-for-fast-inference


Single-Head Vision Transformer with Memory-Efficient Macro and Micro Design for Fast Inference
