{"list":"other","total":76,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"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":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"1807.00431","title":"Confounding variables can degrade generalization performance of radiological deep learning models","created":"2018-07-02","cited_by_count":379},{"id":"1802.03916","title":"Detecting and Correcting for Label Shift with Black Box Predictors","created":"2018-02-12","cited_by_count":366},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"1904.07451","title":"Counterfactual Visual Explanations","created":"2019-04-16","cited_by_count":313},{"id":"1901.09392","title":"On the (In)fidelity and Sensitivity for Explanations","created":"2019-01-27","cited_by_count":310},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"2002.04692","title":"Invariant Risk Minimization Games","created":"2020-02-11","cited_by_count":188},{"id":"1506.02753","title":"Inverting Visual Representations with Convolutional Networks","created":"2015-06-09","cited_by_count":170},{"id":"1807.08024","title":"Explaining Image Classifiers by Counterfactual Generation","created":"2018-07-20","cited_by_count":144},{"id":"1706.08576","title":"Invariant Causal Prediction for Nonlinear Models","created":"2017-06-26","cited_by_count":140},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"1602.03616","title":"Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks","created":"2016-02-11","cited_by_count":106},{"id":"1711.05611","title":"Interpreting Deep Visual Representations via Network Dissection","created":"2017-11-15","cited_by_count":103},{"id":"2010.13924","title":"Benchmarking Deep Learning Interpretability in Time Series Predictions","created":"2020-10-26","cited_by_count":102},{"id":"1512.02017","title":"Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images","created":"2015-12-07","cited_by_count":93},{"id":"2005.11295","title":"From ImageNet to Image Classification: Contextualizing Progress on Benchmarks","created":"2020-05-22","cited_by_count":90},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82},{"id":"1807.06068","title":"Automated Data Slicing for Model Validation:A Big data - AI Integration Approach","created":"2018-07-16","cited_by_count":70},{"id":"2006.07433","title":"A causal framework for distribution generalization","created":"2020-06-12","cited_by_count":68},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68},{"id":"2010.16412","title":"Empirical or Invariant Risk Minimization? A Sample Complexity Perspective","created":"2020-10-30","cited_by_count":62},{"id":"2012.01750","title":"Understanding Failures of Deep Networks via Robust Feature Extraction","created":"2020-12-03","cited_by_count":56},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56},{"id":"1301.2312","title":"Causal Discovery from Changes","created":"2013-01-10","cited_by_count":52},{"id":"1808.00196","title":"Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models","created":"2018-08-01","cited_by_count":50},{"id":"1809.07424","title":"Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure","created":"2018-09-19","cited_by_count":49},{"id":"2004.11457","title":"Debiasing Skin Lesion Datasets and Models? Not So Fast","created":"2020-04-23","cited_by_count":43},{"id":"2006.13913","title":"Generative causal explanations of black-box classifiers","created":"2020-06-24","cited_by_count":41},{"id":"2102.13128","title":"An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization","created":"2021-02-25","cited_by_count":30},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30},{"id":"1902.00407","title":"Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation","created":"2019-02-01","cited_by_count":22},{"id":"2006.07544","title":"Risk Variance Penalization","created":"2020-06-13","cited_by_count":21},{"id":"1910.12370","title":"Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks","created":"2019-10-27","cited_by_count":20},{"id":"1904.07478","title":"GradMask: Reduce Overfitting by Regularizing Saliency","created":"2019-04-16","cited_by_count":12}],"next_cursor":null}