用递归小模型替代深层网络，实现低参数高效率图像分类
Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement
- 用一个3层小模块反复迭代替换原版ViT的多层结构
- 参数量仅为CNN的1/6、ViT的1/84，准确率仍接近主流模型
- 适合边缘设备部署，尤其关注轻量化视觉模型的研究者
深度学习在计算机视觉中的成功依赖于不断扩展的模型规模，从深层卷积神经网络（CNN）到大型视觉变换器（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。受小型递归模型（TRM）的启发，该模型通过迭代状态精炼解决复杂推理任务，我们提出 extbf{视觉小型递归模型（ViTRM）}：将L层ViT编码器替换为一个单一的微型k层块（k=3），递归应用N次。尽管参数量比基于CNN的模型少最多6倍，比ViT少84倍，ViTRM在CIFAR-10和CIFAR-100上仍保持有竞争力的性能。这表明递归计算是视觉任务中替代模型深度的一种可行、高效的路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。