Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information ICML 2021

Explanations for Monotonic Classifiers. ICML 2021

Versatile Verification of Tree Ensembles ICML 2021

Explaining Time Series Predictions with Dynamic Masks ICML 2021

Towards the Explainability of Multimodal Speech Emotion Recognition INTERSPEECH 2021

On the Robustness of Vision Transformers to Adversarial Examples ICCV 2021

Detecting Persuasive Atypicality by Modeling Contextual Compatibility ICCV 2021

Membership Inference Attacks Are Easier on Difficult Problems ICCV 2021

Towards Interpretable Deep Networks for Monocular Depth Estimation ICCV 2021

Explainable Person Re-Identification With Attribute-Guided Metric Distillation ICCV 2021

Beyond Trivial Counterfactual Explanations With Diverse Valuable Explanations ICCV 2021

Explaining Local, Global, and Higher-Order Interactions in Deep Learning ICCV 2021

Architecture Disentanglement for Deep Neural Networks ICCV 2021

Explanations for Occluded Images ICCV 2021

ID-Reveal: Identity-Aware DeepFake Video Detection ICCV 2021

Towards Better Explanations of Class Activation Mapping ICCV 2021

Towards Benchmarking the Utility of Explanations for Model Debugging NAACL 2021

Interpreting Text Classifiers by Learning Context-sensitive Influence of Words NAACL 2021

xER: An Explainable Model for Entity Resolution using an Efficient Solution for the Clique Partitioning Problem NAACL 2021

Accountable Error Characterization NAACL 2021

Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractorwith an Explanation Decoder NAACL 2021

Evaluating Deception Detection Model Robustness To Linguistic Variation NAACL 2021

Understanding and Interpreting the Impact of User Context in Hate Speech Detection NAACL 2021

Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems AAAI 2021

Disentangled Representation Learning in Heterogeneous Information Network for Large-scale Android Malware Detection in the COVID-19 Era and Beyond AAAI 2021