{"list":"other","total":53,"rows":[{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"1902.07208","title":"Transfusion: Understanding Transfer Learning for Medical Imaging","created":"2019-02-14","cited_by_count":368},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"1802.07810","title":"Manipulating and Measuring Model Interpretability","created":"2018-02-21","cited_by_count":256},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"1909.13584","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","created":"2019-09-30","cited_by_count":145},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"id":"1912.01451","title":"Sanity Checks for Saliency Metrics","created":"2019-11-29","cited_by_count":119},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"1911.06473","title":"\"How do I fool you?\": Manipulating User Trust via Misleading Black Box Explanations","created":"2019-11-15","cited_by_count":111},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88},{"id":"2002.00772","title":"Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study","created":"2020-02-03","cited_by_count":86},{"id":"2007.09969","title":"Fairwashing Explanations with Off-Manifold Detergent","created":"2020-07-20","cited_by_count":72},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66},{"id":"1805.07039","title":"A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations","created":"2018-05-18","cited_by_count":60},{"id":"2012.04104","title":"Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately","created":"2020-12-07","cited_by_count":52},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52},{"id":"2010.13233","title":"Now You See Me (CME): Concept-based Model Extraction","created":"2020-10-25","cited_by_count":51},{"id":"1811.03695","title":"Deep Learning Predicts Hip Fracture using Confounding Patient and Healthcare Variables","created":"2018-11-08","cited_by_count":50},{"id":"2008.11721","title":"How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labels","created":"2020-08-26","cited_by_count":39},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38},{"id":"2007.12248","title":"Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction","created":"2020-07-23","cited_by_count":36},{"id":"1906.10670","title":"Improving performance of deep learning models with axiomatic attribution priors and expected gradients","created":"2019-06-25","cited_by_count":32},{"id":"2007.11500","title":"Debiasing Concept-based Explanations with Causal Analysis","created":"2020-07-22","cited_by_count":32},{"id":"2105.06506","title":"Sanity Simulations for Saliency Methods","created":"2021-05-13","cited_by_count":15}],"next_cursor":null}