# Channel Scaling: A Scale-and-Select Approach for Transfer Learning

arXiv: https://arxiv.org/abs/2103.12228 · HTML: https://mlsanity.com/paper/2103.12228/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 14 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 12 of 12)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [SpotTune: Transfer Learning through Adaptive Fine-tuning](https://mlsanity.com/paper/1811.08737/) (2018)
- [SegNAS3D: Network Architecture Search with Derivative-Free Global Optimization for 3D Image Segmentation](https://mlsanity.com/paper/1909.05962/) (2019)

## Abstract (arXiv)

Transfer learning with pre-trained neural networks is a common strategy for training classifiers in medical image analysis. Without proper channel selections, this often results in unnecessarily large models that hinder deployment and explainability. In this paper, we propose a novel approach to efficiently build small and well performing networks by introducing the channel-scaling layers. A channel-scaling layer is attached to each frozen convolutional layer, with the trainable scaling weights inferring the importance of the corresponding feature channels. Unlike the fine-tuning approaches, we maintain the weights of the original channels and large datasets are not required. By imposing L1 regularization and thresholding on the scaling weights, this framework iteratively removes unnecessary feature channels from a pre-trained model. Using an ImageNet pre-trained VGG16 model, we demonstrate the capabilities of the proposed framework on classifying opacity from chest X-ray images. The results show that we can reduce the number of parameters by 95% while delivering a superior performance.