Interpretability

A Novel Visual Interpretability for Deep Neural Networks by Optimizing Activation Maps with Perturbation AAAI 2021 CAMERAS: Enhanced Resolution and Sanity Preserving Class Activation Mapping for Image Saliency CVPR 2021 Do Input Gradients Highlight Discriminative Features? NeurIPS 2021 Enhanced Regularizers for Attributional Robustness AAAI 2021 Enriching ImageNet With Human Similarity Judgments and Psychological Embeddings CVPR 2021 Explainable Models with Consistent Interpretations AAAI 2021 Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation AAAI 2021 IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers NeurIPS 2021 Interpreting Multivariate Shapley Interactions in DNNs AAAI 2021 Learning Logic Rules for Document-Level Relation Extraction EMNLP 2021 Relevance-CAM: Your Model Already Knows Where To Look CVPR 2021 Towards robust vision by multi-task learning on monkey visual cortex NeurIPS 2021 A Diagnostic Study of Explainability Techniques for Text Classification EMNLP 2020 Attack to Explain Deep Representation CVPR 2020 Attribution in Scale and Space CVPR 2020 Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning NeurIPS 2020 Scalable Uncertainty for Computer Vision With Functional Variational Inference CVPR 2020 There and Back Again: Revisiting Backpropagation Saliency Methods CVPR 2020 Towards Visually Explaining Variational Autoencoders CVPR 2020 Attention Branch Network: Learning of Attention Mechanism for Visual Explanation CVPR 2019 Classifier-Agnostic Saliency Map Extraction AAAI 2019 Deliberative Explanations: visualizing network insecurities NeurIPS 2019 Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks CVPR 2019 Excitation Backprop for RNNs CVPR 2018 Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules? EMNLP 2018