2018 · 56 citations · 18 references
ComputingComputer ScienceComputer VisionKnowledge RepresentationMachine LearningDeep LearningExplainable Machine LearningExplanationNetwork InferenceNeural NetworksRepresentation LearningConcept-based ExplanationsConvolutional Neural NetworksDeep Image FeaturesInterpretable Neural NetworksNeural Network InterpretabilityVisual Explanations
We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) can be used to extract the “essence” of what the network learned about a class, and (3) isolate individual features the network uses to make decisions and distinguish related classes.
18
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das et al. · 2017 · 21.6K citations
Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 2016 · 15.2K citations
Learning Deep Features for Discriminative Localization
Bolei Zhou, Aditya Khosla, Àgata Lapedriza et al. · 2016 · 10.8K citations · Full text