{"list":"other","total":73,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"1410.0759","title":"cuDNN: Efficient Primitives for Deep Learning","created":"2014-10-03","cited_by_count":245},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"1808.00278","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","created":"2018-08-01","cited_by_count":235},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170},{"id":"1909.10788","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","created":"2019-09-24","cited_by_count":169},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108},{"id":"1509.09308","title":"Fast Algorithms for Convolutional Neural Networks","created":"2015-09-30","cited_by_count":102},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"1909.13863","title":"XNOR-Net++: Improved Binary Neural Networks","created":"2019-09-30","cited_by_count":97},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88},{"id":"2204.05525","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","created":"2022-04-12","cited_by_count":82},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79},{"id":"1711.00205","title":"Towards Effective Low-bitwidth Convolutional Neural Networks","created":"2017-11-01","cited_by_count":78},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73},{"id":"1810.00861","title":"ProxQuant: Quantized Neural Networks via Proximal Operators","created":"2018-10-01","cited_by_count":59},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52},{"id":"1709.01134","title":"WRPN: Wide Reduced-Precision Networks","created":"2017-09-04","cited_by_count":51},{"id":"2106.11309","title":"How Do Adam and Training Strategies Help BNNs Optimization?","created":"2021-06-21","cited_by_count":46},{"id":"2111.15127","title":"A Unified Pruning Framework for Vision Transformers","created":"2021-11-30","cited_by_count":40},{"id":"1806.07550","title":"Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?","created":"2018-06-20","cited_by_count":39},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37},{"id":"2010.03558","title":"High-Capacity Expert Binary Networks","created":"2020-10-07","cited_by_count":34},{"id":"2012.15823","title":"Binary Graph Neural Networks","created":"2020-12-31","cited_by_count":34},{"id":"1910.10853","title":"Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation","created":"2019-10-24","cited_by_count":28},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21},{"id":"1802.06367","title":"Efficient Sparse-Winograd Convolutional Neural Networks","created":"2018-02-18","cited_by_count":20},{"id":"2111.03481","title":"Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers","created":"2021-11-05","cited_by_count":19},{"id":"2006.16578","title":"Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs","created":"2020-06-30","cited_by_count":14},{"id":"1909.09934","title":"Structured Binary Neural Networks for Image Recognition","created":"2019-09-22","cited_by_count":10},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9},{"id":"2205.07433","title":"Binarizing by Classification: Is soft function really necessary?","created":"2022-05-16","cited_by_count":2}],"next_cursor":null}