{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"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":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"2211.15736","title":"Post-training Quantization on Diffusion Models","created":"2022-11-28","cited_by_count":267},{"id":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180},{"id":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"id":"1811.05181","title":"Gradient Harmonized Single-stage Detector","created":"2018-11-13","cited_by_count":114},{"id":"1702.04008","title":"Soft Weight-Sharing for Neural Network Compression","created":"2017-02-13","cited_by_count":99},{"id":"2003.03603","title":"Generative Low-bitwidth Data Free Quantization","created":"2020-03-07","cited_by_count":88},{"id":"2005.04136","title":"Data-Free Network Quantization With Adversarial Knowledge Distillation","created":"2020-05-08","cited_by_count":80},{"id":"1712.01048","title":"Adaptive Quantization for Deep Neural Network","created":"2017-12-04","cited_by_count":67},{"id":"2103.01049","title":"Diversifying Sample Generation for Accurate Data-Free Quantization","created":"2021-03-01","cited_by_count":63},{"id":"2203.02250","title":"Patch Similarity Aware Data-Free Quantization for Vision Transformers","created":"2022-03-04","cited_by_count":56},{"id":"2202.07471","title":"SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation","created":"2022-02-14","cited_by_count":55},{"id":"1912.01274","title":"The Knowledge Within: Methods for Data-Free Model Compression","created":"2019-12-03","cited_by_count":54},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44},{"id":"2111.09136","title":"IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization","created":"2021-11-17","cited_by_count":43},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42},{"id":"2111.02625","title":"Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples","created":"2021-11-04","cited_by_count":40},{"id":"2303.06869","title":"Adaptive Data-Free Quantization","created":"2023-03-13","cited_by_count":26},{"id":"2009.14502","title":"Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks","created":"2020-09-30","cited_by_count":21},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20},{"id":"2105.12151","title":"AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression","created":"2021-05-25","cited_by_count":17},{"id":"2212.04780","title":"Genie: Show Me the Data for Quantization","created":"2022-12-09","cited_by_count":17},{"id":"2407.05266","title":"CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs","created":"2024-07-07","cited_by_count":17},{"id":"2303.13826","title":"Hard Sample Matters a Lot in Zero-Shot Quantization","created":"2023-03-24","cited_by_count":15},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15},{"id":"1803.09588","title":"Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy","created":"2018-03-26","cited_by_count":14},{"id":"2302.09572","title":"Rethinking Data-Free Quantization as a Zero-Sum Game","created":"2023-02-19","cited_by_count":13},{"id":"2308.03449","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","created":"2023-08-07","cited_by_count":11},{"id":"1911.10739","title":"Empirical Study of Easy and Hard Examples in CNN Training","created":"2019-11-25","cited_by_count":9},{"id":"2109.04186","title":"Fine-grained Data Distribution Alignment for Post-Training Quantization","created":"2021-09-09","cited_by_count":9},{"id":"2201.02620","title":"Compressing Models with Few Samples: Mimicking then Replacing","created":"2022-01-07","cited_by_count":8},{"id":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","cited_by_count":6},{"id":"2303.09230","title":"Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval","created":"2023-03-16","cited_by_count":6}],"next_cursor":null}