{"list":"other","total":52,"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"id":"1910.02600","title":"Deep Evidential Regression","created":"2019-10-07","cited_by_count":355},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1703.01961","title":"Multiplicative Normalizing Flows for Variational Bayesian Neural Networks","created":"2017-03-06","cited_by_count":157},{"id":"1811.12709","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","created":"2018-11-30","cited_by_count":143},{"id":"1512.07666","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","created":"2015-12-23","cited_by_count":121},{"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":"2206.07275","title":"CARD: Classification and Regression Diffusion Models","created":"2022-06-15","cited_by_count":103},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69},{"id":"1908.09961","title":"Theory and Evaluation Metrics for Learning Disentangled Representations","created":"2019-08-26","cited_by_count":57},{"id":"2110.10804","title":"Identifiable Deep Generative Models via Sparse Decoding","created":"2021-10-20","cited_by_count":54},{"id":"2010.12016","title":"Towards falsifiable interpretability research","created":"2020-10-22","cited_by_count":53},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44},{"id":"2002.07965","title":"Being Bayesian about Categorical Probability","created":"2020-02-19","cited_by_count":35},{"id":"1709.00614","title":"On Identifiability of Nonnegative Matrix Factorization","created":"2017-09-02","cited_by_count":34},{"id":"1803.01328","title":"WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling","created":"2018-03-04","cited_by_count":32},{"id":"1912.08416","title":"Benchmarking the Neural Linear Model for Regression","created":"2019-12-18","cited_by_count":31},{"id":"1610.02287","title":"The Generalized Reparameterization Gradient","created":"2016-10-07","cited_by_count":30},{"id":"2006.11590","title":"Regression Prior Networks","created":"2020-06-20","cited_by_count":28},{"id":"2103.04181","title":"Contextual Dropout: An Efficient Sample-Dependent Dropout Module","created":"2021-03-06","cited_by_count":26},{"id":"2107.02757","title":"Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network","created":"2021-06-30","cited_by_count":23},{"id":"2202.11479","title":"Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF","created":"2022-02-23","cited_by_count":23},{"id":"1610.05683","title":"Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms","created":"2016-10-18","cited_by_count":22},{"id":"2403.12459","title":"Non-negative Contrastive Learning","created":"2024-03-19","cited_by_count":19},{"id":"1511.02199","title":"The Poisson Gamma Belief Network","created":"2015-11-06","cited_by_count":10},{"id":"1509.01631","title":"Stochastic gradient variational Bayes for gamma approximating distributions","created":"2015-09-04","cited_by_count":9},{"id":"2305.10406","title":"Variational Classification","created":"2023-05-17","cited_by_count":5},{"id":"2408.03388","title":"A Non-negative VAE:the Generalized Gamma Belief Network","created":"2024-08-06","cited_by_count":4},{"id":"2206.08022","title":"Partial Identifiability for Nonnegative Matrix Factorization","created":"2022-06-16","cited_by_count":3},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2}],"next_cursor":null}