{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"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":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","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":"1710.04806","title":"Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions","created":"2017-10-13","cited_by_count":234},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"1907.07165","title":"Explaining Classifiers with Causal Concept Effect (CaCE)","created":"2019-07-16","cited_by_count":135},{"id":"1903.06256","title":"Learning Robust Representations by Projecting Superficial Statistics Out","created":"2019-03-02","cited_by_count":123},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85},{"id":"2008.06775","title":"Model Patching: Closing the Subgroup Performance Gap with Data Augmentation","created":"2020-08-15","cited_by_count":83},{"id":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2010.05981","title":"Shape-Texture Debiased Neural Network Training","created":"2020-10-12","cited_by_count":76},{"id":"2108.10008","title":"BiaSwap: Removing dataset bias with bias-tailored swapping augmentation","created":"2021-08-23","cited_by_count":70},{"id":"1806.01822","title":"Relational recurrent neural networks","created":"2018-06-05","cited_by_count":65},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"2110.03095","title":"Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective","created":"2021-10-06","cited_by_count":57},{"id":"2010.13233","title":"Now You See Me (CME): Concept-based Model Extraction","created":"2020-10-25","cited_by_count":51},{"id":"2106.06804","title":"Entropy-based Logic Explanations of Neural Networks","created":"2021-06-12","cited_by_count":51},{"id":"1603.05631","title":"Generative Image Modeling using Style and Structure Adversarial Networks","created":"2016-03-17","cited_by_count":50},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46},{"id":"1907.09720","title":"Metalearned Neural Memory","created":"2019-07-23","cited_by_count":44},{"id":"1904.12543","title":"Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization","created":"2019-04-29","cited_by_count":43},{"id":"2002.08822","title":"Automatic Shortcut Removal for Self-Supervised Representation Learning","created":"2020-02-20","cited_by_count":43},{"id":"2011.11486","title":"Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks","created":"2020-11-19","cited_by_count":16},{"id":"1703.04096","title":"Improving Interpretability of Deep Neural Networks with Semantic Information","created":"2017-03-12","cited_by_count":15},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7},{"id":"2205.11722","title":"Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments","created":"2022-05-24","cited_by_count":3}],"next_cursor":null}