{"list":"other","total":71,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"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":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2203.10807","title":"ViM: Out-Of-Distribution with Virtual-logit Matching","created":"2022-03-21","cited_by_count":405},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150},{"id":"2006.12024","title":"Bayesian Neural Networks: An Introduction and Survey","created":"2020-06-22","cited_by_count":131},{"id":"2011.11156","title":"Better Aggregation in Test-Time Augmentation","created":"2020-11-23","cited_by_count":122},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"id":"2203.07724","title":"CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving","created":"2022-03-15","cited_by_count":100},{"id":"2012.08334","title":"Masksembles for Uncertainty Estimation","created":"2020-12-15","cited_by_count":88},{"id":"2010.14689","title":"Bayesian Deep Learning via Subnetwork Inference","created":"2020-10-28","cited_by_count":87},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80},{"id":"1802.06455","title":"Bayesian Uncertainty Estimation for Batch Normalized Deep Networks","created":"2018-02-18","cited_by_count":70},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49},{"id":"2208.07591","title":"Uncertainty-guided Source-free Domain Adaptation","created":"2022-08-16","cited_by_count":46},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41},{"id":"1912.11316","title":"TRADI: Tracking deep neural network weight distributions for uncertainty estimation","created":"2019-12-24","cited_by_count":39},{"id":"1805.11614","title":"Deep Learning under Privileged Information Using Heteroscedastic Dropout","created":"2018-05-29","cited_by_count":27},{"id":"2203.01437","title":"MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks","created":"2022-03-02","cited_by_count":24},{"id":"2001.08049","title":"On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation","created":"2020-01-22","cited_by_count":23},{"id":"2012.02818","title":"Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification","created":"2020-12-04","cited_by_count":18},{"id":"2303.08010","title":"Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models","created":"2023-03-14","cited_by_count":16},{"id":"2310.08287","title":"A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors","created":"2023-10-12","cited_by_count":12},{"id":"2206.07673","title":"Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling","created":"2022-06-15","cited_by_count":9}],"next_cursor":null}