{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"1806.11146","title":"Adversarial Reprogramming of Neural Networks","created":"2018-06-28","cited_by_count":116},{"id":"1906.02773","title":"One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers","created":"2019-06-06","cited_by_count":102},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91},{"id":"2211.11635","title":"Understanding and Improving Visual Prompting: A Label-Mapping Perspective","created":"2022-11-21","cited_by_count":87},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2007.08714","title":"Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources","created":"2020-07-17","cited_by_count":83},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50},{"id":"2012.12235","title":"Unadversarial Examples: Designing Objects for Robust Vision","created":"2020-12-22","cited_by_count":45},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44},{"id":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41},{"id":"2102.07325","title":"Cross-modal Adversarial Reprogramming","created":"2021-02-15","cited_by_count":34},{"id":"2209.10222","title":"Fairness Reprogramming","created":"2022-09-21","cited_by_count":33},{"id":"1905.07785","title":"Sparse Transfer Learning via Winning Lottery Tickets","created":"2019-05-19","cited_by_count":27},{"id":"2103.01542","title":"TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning","created":"2021-03-02","cited_by_count":25},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17},{"id":"2301.02120","title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning","created":"2023-01-05","cited_by_count":12},{"id":"2105.00227","title":"On the Adversarial Robustness of Quantized Neural Networks","created":"2021-05-01","cited_by_count":11},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10},{"id":"1909.12741","title":"Impact of Low-bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networks","created":"2019-09-27","cited_by_count":9},{"id":"2002.03875","title":"Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration","created":"2020-02-10","cited_by_count":6},{"id":"2302.09369","title":"Calibrating the Rigged Lottery: Making All Tickets Reliable","created":"2023-02-18","cited_by_count":4},{"id":"2304.11834","title":"Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning","created":"2023-04-24","cited_by_count":3},{"id":"2306.12190","title":"Quantifying lottery tickets under label noise: accuracy, calibration, and complexity","created":"2023-06-21","cited_by_count":2},{"id":"2308.13960","title":"Sparse Models for Machine Learning","created":"2023-08-26","cited_by_count":1}],"next_cursor":null}