{"list":"other","total":61,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"id":"1912.07768","title":"Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data","created":"2019-12-17","cited_by_count":104},{"id":"2006.08572","title":"Flexible Dataset Distillation: Learn Labels Instead of Images","created":"2020-06-15","cited_by_count":91},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84},{"id":"2106.07760","title":"RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning","created":"2021-06-14","cited_by_count":74},{"id":"2207.09653","title":"FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning","created":"2022-07-20","cited_by_count":66},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48},{"id":"2001.05755","title":"ScaIL: Classifier Weights Scaling for Class Incremental Learning","created":"2020-01-16","cited_by_count":47},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46},{"id":"2303.04707","title":"DiM: Distilling Dataset into Generative Model","created":"2023-03-08","cited_by_count":46},{"id":"1910.13540","title":"Small-GAN: Speeding Up GAN Training Using Core-sets","created":"2019-10-29","cited_by_count":41},{"id":"2311.01570","title":"Sequential Subset Matching for Dataset Distillation","created":"2023-11-02","cited_by_count":40},{"id":"2104.08312","title":"Data Shapley Valuation for Efficient Batch Active Learning","created":"2021-04-16","cited_by_count":27},{"id":"2209.14851","title":"Meta Knowledge Condensation for Federated Learning","created":"2022-09-29","cited_by_count":26},{"id":"2310.14019","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","created":"2023-10-21","cited_by_count":20},{"id":"2403.06075","title":"Multisize Dataset Condensation","created":"2024-03-10","cited_by_count":19},{"id":"2310.06982","title":"Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality","created":"2023-10-10","cited_by_count":17},{"id":"2312.01537","title":"Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents","created":"2023-12-03","cited_by_count":16},{"id":"2403.17921","title":"The Need for Speed: Pruning Transformers with One Recipe","created":"2024-03-26","cited_by_count":16},{"id":"2307.03967","title":"End-to-End Supervised Multilabel Contrastive Learning","created":"2023-07-08","cited_by_count":8},{"id":"2306.04147","title":"CFDP: Common Frequency Domain Pruning","created":"2023-06-07","cited_by_count":5},{"id":"2109.05587","title":"On the Efficiency of Subclass Knowledge Distillation in Classification Tasks","created":"2021-09-12","cited_by_count":4},{"id":"2110.06830","title":"CONetV2: Efficient Auto-Channel Size Optimization for CNNs","created":"2021-10-13","cited_by_count":4},{"id":"2104.08314","title":"High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks","created":"2021-04-16","cited_by_count":3},{"id":"2207.08063","title":"Subclass Knowledge Distillation with Known Subclass Labels","created":"2022-07-17","cited_by_count":3},{"id":"2306.07309","title":"A New Probabilistic Distance Metric With Application In Gaussian Mixture Reduction","created":"2023-06-12","cited_by_count":3},{"id":"2401.01448","title":"ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification","created":"2024-01-02","cited_by_count":3}],"next_cursor":null}