{"list":"other","total":51,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"1608.04363","title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","created":"2016-08-15","cited_by_count":85},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82},{"id":"2007.11154","title":"Rethinking CNN Models for Audio Classification","created":"2020-07-22","cited_by_count":48},{"id":"2006.00555","title":"Transferring Inductive Biases through Knowledge Distillation","created":"2020-05-31","cited_by_count":41},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41},{"id":"2106.12378","title":"Co-advise: Cross Inductive Bias Distillation","created":"2021-06-23","cited_by_count":40},{"id":"1810.09050","title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","created":"2018-10-22","cited_by_count":38},{"id":"2104.13497","title":"ConTNet: Why not use convolution and transformer at the same time?","created":"2021-04-27","cited_by_count":38},{"id":"2004.07301","title":"ESResNet: Environmental Sound Classification Based on Visual Domain Models","created":"2020-04-15","cited_by_count":31},{"id":"1912.04761","title":"Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization","created":"2019-12-10","cited_by_count":29},{"id":"2110.07313","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","created":"2021-10-14","cited_by_count":22},{"id":"1706.07156","title":"Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks","created":"2017-06-22","cited_by_count":14},{"id":"1804.09288","title":"A Closer Look at Weak Label Learning for Audio Events","created":"2018-04-24","cited_by_count":12},{"id":"1906.06438","title":"Scalable Syntax-Aware Language Models Using Knowledge Distillation","created":"2019-06-14","cited_by_count":8},{"id":"1909.12699","title":"Urban Sound Tagging using Convolutional Neural Networks","created":"2019-09-27","cited_by_count":7},{"id":"2005.00878","title":"Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking","created":"2020-05-02","cited_by_count":7},{"id":"2107.00623","title":"Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks","created":"2021-07-01","cited_by_count":5},{"id":"2002.09607","title":"Multi-Representation Knowledge Distillation For Audio Classification","created":"2020-02-22","cited_by_count":4},{"id":"2009.01759","title":"Intra-Utterance Similarity Preserving Knowledge Distillation for Audio Tagging","created":"2020-09-03","cited_by_count":4}],"next_cursor":null}