{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"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":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"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":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"1512.02479","title":"Explaining NonLinear Classification Decisions with Deep Taylor Decomposition","created":"2015-12-08","cited_by_count":250},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"1906.04571","title":"Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology","created":"2019-06-11","cited_by_count":200},{"id":"1905.00780","title":"Full-Gradient Representation for Neural Network Visualization","created":"2019-05-02","cited_by_count":191},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"2106.03149","title":"Large-scale Unsupervised Semantic Segmentation","created":"2021-06-06","cited_by_count":101},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"1512.02017","title":"Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images","created":"2015-12-07","cited_by_count":93},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80},{"id":"2204.03632","title":"The Effects of Regularization and Data Augmentation are Class Dependent","created":"2022-04-07","cited_by_count":67},{"id":"2010.05785","title":"Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification","created":"2020-10-09","cited_by_count":63},{"id":"1812.06707","title":"Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation","created":"2018-12-17","cited_by_count":49},{"id":"1904.00605","title":"Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks","created":"2019-04-01","cited_by_count":49},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35},{"id":"1810.03805","title":"What made you do this? Understanding black-box decisions with sufficient input subsets","created":"2018-10-09","cited_by_count":31},{"id":"2003.08907","title":"Overinterpretation reveals image classification model pathologies","created":"2020-03-19","cited_by_count":28},{"id":"1904.07478","title":"GradMask: Reduce Overfitting by Regularizing Saliency","created":"2019-04-16","cited_by_count":12},{"id":"1605.05538","title":"Improving Weakly-Supervised Object Localization By Micro-Annotation","created":"2016-05-18","cited_by_count":11}],"next_cursor":null}