# ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation

arXiv: https://arxiv.org/abs/1812.08934 · HTML: https://mlsanity.com/paper/1812.08934/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2018.

## Built on by (most cited first, 30 of 76)

- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Non-Probability Sampling Network for Stochastic Human Trajectory Prediction](https://mlsanity.com/paper/2203.13471/) (2022)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2101.08467/) (2021)
- [When to Prune? A Policy towards Early Structural Pruning](https://mlsanity.com/paper/2110.12007/) (2021)
- [Auto-Split: A General Framework of Collaborative Edge-Cloud AI](https://mlsanity.com/paper/2108.13041/) (2021)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention](https://mlsanity.com/paper/2211.13955/) (2022)
- [PyGlove: Symbolic Programming for Automated Machine Learning](https://mlsanity.com/paper/2101.08809/) (2021)
- [GradSign: Model Performance Inference with Theoretical Insights](https://mlsanity.com/paper/2110.08616/) (2021)
- [Towards Accurate and Compact Architectures via Neural Architecture Transformer](https://mlsanity.com/paper/2102.10301/) (2021)
- [Adaptive Sharpness-Aware Pruning for Robust Sparse Networks](https://mlsanity.com/paper/2306.14306/) (2023)
- [Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices](https://mlsanity.com/paper/2310.18329/) (2023)
- [HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning](https://mlsanity.com/paper/2106.08630/) (2021)
- [PhiNets: a scalable backbone for low-power AI at the edge](https://mlsanity.com/paper/2110.00337/) (2021)
- [FBNetV5: Neural Architecture Search for Multiple Tasks in One Run](https://mlsanity.com/paper/2111.10007/) (2021)
- [NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization](https://mlsanity.com/paper/2104.00031/) (2021)
- [Rethinking Co-design of Neural Architectures and Hardware Accelerators](https://mlsanity.com/paper/2102.08619/) (2021)
- [Soft Masking for Cost-Constrained Channel Pruning](https://mlsanity.com/paper/2211.02206/) (2022)
- [LANA: Latency Aware Network Acceleration](https://mlsanity.com/paper/2107.10624/) (2021)
- [Learning Versatile Neural Architectures by Propagating Network Codes](https://mlsanity.com/paper/2103.13253/) (2021)
- [NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks](https://mlsanity.com/paper/2401.13330/) (2024)
- [HALP: Hardware-Aware Latency Pruning](https://mlsanity.com/paper/2110.10811/) (2021)
- [One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2111.01203/) (2021)
- [Data-Free Neural Architecture Search via Recursive Label Calibration](https://mlsanity.com/paper/2112.02086/) (2021)
- [Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions](https://mlsanity.com/paper/2203.06810/) (2022)
- [Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2109.07582/) (2021)
- [Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration](https://mlsanity.com/paper/2111.11581/) (2021)
- [Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation](https://mlsanity.com/paper/2209.15560/) (2022)

## Abstract (arXiv)

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, our approach leverages existing efficient network building blocks and focuses on exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints. We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors. At the core of our algorithm lies an accuracy predictor built atop Gaussian Process with Bayesian optimization for iterative sampling. With a one-time building cost for the predictors, our algorithm produces state-of-the-art model architectures on different platforms under given constraints in just minutes. Our results show that adapting computation resources to building blocks is critical to model performance. Without the addition of any bells and whistles, our models achieve significant accuracy improvements against state-of-the-art hand-crafted and automatically designed architectures. We achieve 73.8% and 75.3% top-1 accuracy on ImageNet at 20ms latency on a mobile CPU and DSP. At reduced latency, our models achieve up to 8.5% (4.8%) and 6.6% (9.3%) absolute top-1 accuracy improvements compared to MobileNetV2 and MnasNet, respectively, on a mobile CPU (DSP), and 2.7% (4.6%) and 5.6% (2.6%) accuracy gains over ResNet-101 and ResNet-152, respectively, on an Nvidia GPU (Intel CPU).