{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"id":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"2011.11619","title":"Neural collapse with unconstrained features","created":"2020-11-23","cited_by_count":142},{"id":"2011.14027","title":"General Multi-label Image Classification with Transformers","created":"2020-11-27","cited_by_count":127},{"id":"1901.02324","title":"Learning with Fenchel-Young Losses","created":"2019-01-08","cited_by_count":119},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119},{"id":"2302.03004","title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning","created":"2023-02-06","cited_by_count":116},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102},{"id":"2011.11197","title":"The Emerging Trends of Multi-Label Learning","created":"2020-11-23","cited_by_count":100},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"2110.02796","title":"An Unconstrained Layer-Peeled Perspective on Neural Collapse","created":"2021-10-06","cited_by_count":87},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84},{"id":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78},{"id":"2102.08817","title":"Dissecting Supervised Contrastive Learning","created":"2021-02-17","cited_by_count":64},{"id":"2202.08384","title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","created":"2022-02-17","cited_by_count":63},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46},{"id":"2204.08735","title":"Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning","created":"2022-04-19","cited_by_count":43},{"id":"2204.07596","title":"Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning","created":"2022-04-15","cited_by_count":40},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36},{"id":"1810.07076","title":"Stochastic Negative Mining for Learning with Large Output Spaces","created":"2018-10-16","cited_by_count":29},{"id":"2007.06753","title":"From Symmetry to Geometry: Tractable Nonconvex Problems","created":"2020-07-14","cited_by_count":29},{"id":"1510.06096","title":"When Are Nonconvex Problems Not Scary?","created":"2015-10-21","cited_by_count":28},{"id":"1511.04777","title":"Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method","created":"2015-11-15","cited_by_count":24},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24},{"id":"2303.07608","title":"On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data","created":"2023-03-14","cited_by_count":23},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20},{"id":"2009.07801","title":"Convex Calibrated Surrogates for the Multi-Label F-Measure","created":"2020-09-16","cited_by_count":18},{"id":"2303.06484","title":"Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap","created":"2023-03-11","cited_by_count":14},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13},{"id":"2210.05398","title":"Continual Learning by Modeling Intra-Class Variation","created":"2022-10-11","cited_by_count":12},{"id":"2202.08978","title":"Cyclical Focal Loss","created":"2022-02-16","cited_by_count":8},{"id":"2304.08914","title":"A Study of Neural Collapse Phenomenon: Grassmannian Frame, Symmetry and Generalization","created":"2023-04-18","cited_by_count":7},{"id":"2209.08745","title":"Importance Tempering: Group Robustness for Overparameterized Models","created":"2022-09-19","cited_by_count":6},{"id":"2302.00491","title":"Learning Prototype Classifiers for Long-Tailed Recognition","created":"2023-02-01","cited_by_count":6},{"id":"1410.6990","title":"Local Rademacher Complexity for Multi-label Learning","created":"2014-10-26","cited_by_count":5}],"next_cursor":null}