Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
This work addresses efficiency challenges in visual perception for computer vision applications, representing an incremental improvement by adapting an existing NLP architecture to vision tasks.
The paper tackles the high computational complexity of Transformers in high-resolution image processing by introducing Vision-RWKV, which surpasses ViT in image classification with faster speeds and lower memory usage, and outperforms window-based models in dense prediction tasks.
Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces Vision-RWKV (VRWKV), a model adapted from the RWKV model used in the NLP field with necessary modifications for vision tasks. Similar to the Vision Transformer (ViT), our model is designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage lies in its reduced spatial aggregation complexity, which renders it exceptionally adept at processing high-resolution images seamlessly, eliminating the necessity for windowing operations. Our evaluations demonstrate that VRWKV surpasses ViT's performance in image classification and has significantly faster speeds and lower memory usage processing high-resolution inputs. In dense prediction tasks, it outperforms window-based models, maintaining comparable speeds. These results highlight VRWKV's potential as a more efficient alternative for visual perception tasks. Code is released at https://github.com/OpenGVLab/Vision-RWKV.