# ReStNet: A Reusable & Stitchable Network for Dynamic Adaptation on IoT Devices

arXiv: https://arxiv.org/abs/2506.09066 · HTML: https://mlsanity.com/paper/2506.09066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 58 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [PTQD: Accurate Post-Training Quantization for Diffusion Models](https://mlsanity.com/paper/2305.10657/) (2023)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer](https://mlsanity.com/paper/2210.06707/) (2022)
- [Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning](https://mlsanity.com/paper/1904.11740/) (2019)
- [Backdoor Pre-trained Models Can Transfer to All](https://mlsanity.com/paper/2111.00197/) (2021)
- [Scalable Vision Transformers with Hierarchical Pooling](https://mlsanity.com/paper/2103.10619/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [Similarity and Matching of Neural Network Representations](https://mlsanity.com/paper/2110.14633/) (2021)
- [SepPrune: Structured Pruning for Efficient Deep Speech Separation](https://mlsanity.com/paper/2505.12079/) (2025)
- [Understanding the Dynamics of DNNs Using Graph Modularity](https://mlsanity.com/paper/2111.12485/) (2021)

## Abstract (arXiv)

With the rapid development of deep learning, a growing number of pre-trained models have been publicly available. However, deploying these fixed models in real-world IoT applications is challenging because different devices possess heterogeneous computational and memory resources, making it impossible to deploy a single model across all platforms. Although traditional compression methods, such as pruning, quantization, and knowledge distillation, can improve efficiency, they become inflexible once applied and cannot adapt to changing resource constraints. To address these issues, we propose ReStNet, a Reusable and Stitchable Network that dynamically constructs a hybrid network by stitching two pre-trained models together. Implementing ReStNet requires addressing several key challenges, including how to select the optimal stitching points, determine the stitching order of the two pre-trained models, and choose an effective fine-tuning strategy. To systematically address these challenges and adapt to varying resource constraints, ReStNet determines the stitching point by calculating layer-wise similarity via Centered Kernel Alignment (CKA). It then constructs the hybrid model by retaining early layers from a larger-capacity model and appending deeper layers from a smaller one. To facilitate efficient deployment, only the stitching layer is fine-tuned. This design enables rapid adaptation to changing budgets while fully leveraging available resources. Moreover, ReStNet supports both homogeneous (CNN-CNN, Transformer-Transformer) and heterogeneous (CNN-Transformer) stitching, allowing to combine different model families flexibly. Extensive experiments on multiple benchmarks demonstrate that ReStNet achieve flexible accuracy-efficiency trade-offs at runtime while significantly reducing training cost.