Diverse feature visualizations reveal invariances in early layers of deep neural networks
arXiv:1807.10589
Abstract
Visualizing features in deep neural networks (DNNs) can help understanding their computations. Many previous studies aimed to visualize the selectivity of individual units by finding meaningful images that maximize their activation. However, comparably little attention has been paid to visualizing to what image transformations units in DNNs are invariant. Here we propose a method to discover invariances in the responses of hidden layer units of deep neural networks. Our approach is based on simultaneously searching for a batch of images that strongly activate a unit while at the same time being as distinct from each other as possible. We find that even early convolutional layers in VGG-19 exhibit various forms of response invariance: near-perfect phase invariance in some units and invariance to local diffeomorphic transformations in others. At the same time, we uncover representational differences with ResNet-50 in its corresponding layers. We conclude that invariance transformations are a major computational component learned by DNNs and we provide a systematic method to study them.
arXiv commentAccepted for ECCV 2018
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Image Generation with PixelCNN Decoders
- Pixel Recurrent Neural Networks
- Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway
- Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Texture Synthesis Using Convolutional Neural Networks
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
- Understanding Intra-Class Knowledge Inside CNN
- Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations