# Towards Accurate and Compact Architectures via Neural Architecture Transformer

arXiv: https://arxiv.org/abs/2102.10301 · HTML: https://mlsanity.com/paper/2102.10301/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 73 references that are in the map.
- First posted on arXiv 20 Feb 2021.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [SNAS: Stochastic Neural Architecture Search](https://mlsanity.com/paper/1812.09926/) (2018)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)

## Built on by (most cited first, 17 of 17)

- [EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2106.15277/) (2021)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Improving Robustness by Enhancing Weak Subnets](https://mlsanity.com/paper/2201.12765/) (2022)
- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [Improving Fine-tuning of Self-supervised Models with Contrastive Initialization](https://mlsanity.com/paper/2208.00238/) (2022)
- [Performance-aware Approximation of Global Channel Pruning for Multitask CNNs](https://mlsanity.com/paper/2303.11923/) (2023)
- [Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images](https://mlsanity.com/paper/2211.10643/) (2022)
- [Boosting Semi-Supervised Learning with Contrastive Complementary Labeling](https://mlsanity.com/paper/2212.06643/) (2022)
- [Pareto-aware Neural Architecture Generation for Diverse Computational Budgets](https://mlsanity.com/paper/2210.07634/) (2022)
- [Content-Aware Convolutional Neural Networks](https://mlsanity.com/paper/2106.15797/) (2021)
- [Compact Model Training by Low-Rank Projection with Energy Transfer](https://mlsanity.com/paper/2204.05566/) (2022)
- [Automated Dominative Subspace Mining for Efficient Neural Architecture Search](https://mlsanity.com/paper/2210.17180/) (2022)
- [Neural Architecture Retrieval](https://mlsanity.com/paper/2307.07919/) (2023)
- [FlowNAS: Neural Architecture Search for Optical Flow Estimation](https://mlsanity.com/paper/2207.01271/) (2022)
- [MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency](https://mlsanity.com/paper/2310.15074/) (2023)
- [AV-Unified: A Unified Framework for Audio-visual Scene Understanding](https://mlsanity.com/paper/2603.06530/) (2026)

## Abstract (arXiv)

Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Neural Architecture Search (NAS) methods. However, even a well-designed/searched architecture may still contain many nonsignificant or redundant modules/operations. Thus, it is necessary to optimize the operations inside an architecture to improve the performance without introducing extra computational cost. To this end, we have proposed a Neural Architecture Transformer (NAT) method which casts the optimization problem into a Markov Decision Process (MDP) and seeks to replace the redundant operations with more efficient operations, such as skip or null connection. Note that NAT only considers a small number of possible transitions and thus comes with a limited search/transition space. As a result, such a small search space may hamper the performance of architecture optimization. To address this issue, we propose a Neural Architecture Transformer++ (NAT++) method which further enlarges the set of candidate transitions to improve the performance of architecture optimization. Specifically, we present a two-level transition rule to obtain valid transitions, i.e., allowing operations to have more efficient types (e.g., convolution->separable convolution) or smaller kernel sizes (e.g., 5x5->3x3). Note that different operations may have different valid transitions. We further propose a Binary-Masked Softmax (BMSoftmax) layer to omit the possible invalid transitions. Extensive experiments on several benchmark datasets show that the transformed architecture significantly outperforms both its original counterpart and the architectures optimized by existing methods.