Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation
arXiv:1712.08268 · doi:10.1016/j.imavis.2019.02.005
Abstract
Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge. In this paper, we propose a novel two-step understanding method, namely Salient Relevance (SR) map, which aims to shed light on how deep CNNs recognize images and learn features from areas, referred to as attention areas, therein. Our proposed method starts out with a layer-wise relevance propagation (LRP) step which estimates a pixel-wise relevance map over the input image. Following, we construct a context-aware saliency map, SR map, from the LRP-generated map which predicts areas close to the foci of attention instead of isolated pixels that LRP reveals. In human visual system, information of regions is more important than of pixels in recognition. Consequently, our proposed approach closely simulates human recognition. Experimental results using the ILSVRC2012 validation dataset in conjunction with two well-established deep CNN models, AlexNet and VGG-16, clearly demonstrate that our proposed approach concisely identifies not only key pixels but also attention areas that contribute to the underlying neural network's comprehension of the given images. As such, our proposed SR map constitutes a convenient visual interface which unveils the visual attention of the network and reveals which type of objects the model has learned to recognize after training. The source code is available at https://github.com/Hey1Li/Salient-Relevance-Propagation.
arXiv comment35 pages, 15 figures
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- Understanding Neural Networks Through Deep Visualization
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- SmoothGrad: removing noise by adding noise
- DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Describing Multimedia Content using Attention-based Encoder--Decoder Networks
- Learning how to explain neural networks: PatternNet and PatternAttribution
- The (Un)reliability of saliency methods
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
- Understanding Intra-Class Knowledge Inside CNN
- ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models