Semantics for Global and Local Interpretation of Deep Neural Networks
arXiv:1910.09085
Abstract
Deep neural networks (DNNs) with high expressiveness have achieved state-of-the-art performance in many tasks. However, their distributed feature representations are difficult to interpret semantically. In this work, human-interpretable semantic concepts are associated with vectors in feature space. The association process is mathematically formulated as an optimization problem. The semantic vectors obtained from the optimal solution are applied to interpret deep neural networks globally and locally. The global interpretations are useful to understand the knowledge learned by DNNs. The interpretation of local behaviors can help to understand individual decisions made by DNNs better. The empirical experiments demonstrate how to use identified semantics to interpret the existing DNNs.
References in corpus (9)
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- SmoothGrad: removing noise by adding noise
- Object Detectors Emerge in Deep Scene CNNs
- Sanity Checks for Saliency Maps
- 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
Cited by in corpus (4)
- Verification of Size Invariance in DNN Activations using Concept Embeddings
- Contextual Prediction Difference Analysis for Explaining Individual Image Classifications
- Introspective Learning by Distilling Knowledge from Online Self-explanation
- Reproduction of Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection