Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917376676593664 |
|---|---|
| author | Akazan, Ange-Clément Koroko, Abdoulaye Mbingui, Verlon Roel Arinloye, Choukouriyah Fifen, Hassan Bandolo, Rose |
| author_facet | Akazan, Ange-Clément Koroko, Abdoulaye Mbingui, Verlon Roel Arinloye, Choukouriyah Fifen, Hassan Bandolo, Rose |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19503 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement Akazan, Ange-Clément Koroko, Abdoulaye Mbingui, Verlon Roel Arinloye, Choukouriyah Fifen, Hassan Bandolo, Rose Computer Vision and Pattern Recognition 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. |
| title | Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.19503 |