# Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis

arXiv: https://arxiv.org/abs/2306.10128 · HTML: https://mlsanity.com/paper/2306.10128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 16 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [Intrinsic dimension of data representations in deep neural networks](https://mlsanity.com/paper/1905.12784/) (2019)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [BAM: Bottleneck Attention Module](https://mlsanity.com/paper/1807.06514/) (2018)
- [Analyzing and Improving Representations with the Soft Nearest Neighbor Loss](https://mlsanity.com/paper/1902.01889/) (2019)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Hierarchical nucleation in deep neural networks](https://mlsanity.com/paper/2007.03506/) (2020)
- [FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis](https://mlsanity.com/paper/1809.05989/) (2018)
- [TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices](https://mlsanity.com/paper/2008.04245/) (2020)
- [Inter-layer Information Similarity Assessment of Deep Neural Networks Via Topological Similarity and Persistence Analysis of Data Neighbour Dynamics](https://mlsanity.com/paper/2012.03793/) (2020)

## Abstract (arXiv)

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune for the application at hand. In this work we propose a novel type of DNN analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRepSim) which can be used to identify specific design interventions that lead to more efficient self-attention convolutional neural network architectures. Using insights grained from ClassRepSim we propose the Spatial Transformed Attention Condenser (STAC) module, a novel attention-condenser based self-attention module. We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy compared to vanilla ResNet models and up to a 0.5% increase in top-1 accuracy compared to SENet models on the ImageNet64x64 dataset, at the cost of up to 1.7% increase in FLOPs and 2x the number of parameters. In addition, we demonstrate that results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance compared to an extensive parameter search.