# IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification

arXiv: https://arxiv.org/abs/1804.10123 · HTML: https://mlsanity.com/paper/1804.10123/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2018.

## Built on by (most cited first, 12 of 12)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning](https://mlsanity.com/paper/2401.03230/) (2024)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [GradMDM: Adversarial Attack on Dynamic Networks](https://mlsanity.com/paper/2304.06724/) (2023)
- [Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss](https://mlsanity.com/paper/2102.09808/) (2021)
- [Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation](https://mlsanity.com/paper/2111.06500/) (2021)
- [TinyMLOps: Operational Challenges for Widespread Edge AI Adoption](https://mlsanity.com/paper/2203.10923/) (2022)
- [Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks](https://mlsanity.com/paper/2111.12330/) (2021)
- [SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks](https://mlsanity.com/paper/2207.10237/) (2022)
- [Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles](https://mlsanity.com/paper/2312.10264/) (2023)
- [Puppet-CNN: Continuous Parameter Dynamics for Input-Adaptive Convolutional Networks](https://mlsanity.com/paper/2411.12876/) (2024)

## Abstract (arXiv)

Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding vanishing gradients. These shortcut connections have interesting side-effects that make ResNets behave differently from other typical network architectures. In this work we use these properties to design a network based on a ResNet but with parameter sharing and with adaptive computation time. The resulting network is much smaller than the original network and can adapt the computational cost to the complexity of the input image.