视觉微递归模型(ViTRM):通过递归状态细化实现参数高效的图像分类
Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement
AI总结:
本文提出ViTRM,通过递归状态细化替代传统深度架构,实现参数高效图像分类,在CIFAR-10和CIFAR-100上表现优异。
摘要:
深度学习在计算机视觉中的成功得益于模型规模的增加,从深层卷积神经网络(CNN)到大视觉变换器(ViT)。尽管有效,这些架构参数密集且需要大量计算资源,限制了在资源受限环境中的部署。受微递归模型(TRM)启发,后者表明小递归网络可通过迭代状态细化解决复杂推理任务,本文引入视觉微递归模型(ViTRM):一种参数高效的架构,用单个微小k层块(k=3)递归应用N次,替代L层ViT编码器。尽管参数数量比CNN和ViT分别少6倍和84倍,ViTRM在CIFAR-10和CIFAR-100上仍保持竞争力,证明递归计算是视觉领域替代深度架构的可行且参数高效的替代方案。
英文摘要:
The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are parameter-intensive and demand significant computational resources, limiting deployment in resource-constrained environments. Inspired by Tiny Recursive Models (TRM), which show that small recursive networks can solve complex reasoning tasks through iterative state refinement, we introduce the \textbf{Vision Tiny Recursion Model (ViTRM)}: a parameter-efficient architecture that replaces the $L$-layer ViT encoder with a single tiny $k$-layer block ($k{=}3$) applied recursively $N$ times. Despite using up to $6 \times $ and $84 \times$ fewer parameters than CNN based models and ViT respectively, ViTRM maintains competitive performance on CIFAR-10 and CIFAR-100. This demonstrates that recursive computation is a viable, parameter-efficient alternative to architectural depth in vision.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。