{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2201.01266","title":"Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images","created":"2022-01-04","cited_by_count":830},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"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":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2111.12293","title":"PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization","created":"2021-11-24","cited_by_count":179},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151},{"id":"2206.14718","title":"LViT: Language meets Vision Transformer in Medical Image Segmentation","created":"2022-06-29","cited_by_count":111},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98},{"id":"2103.05940","title":"TransMed: Transformers Advance Multi-modal Medical Image Classification","created":"2021-03-10","cited_by_count":86},{"id":"2002.00104","title":"Post-Training Piecewise Linear Quantization for Deep Neural Networks","created":"2020-01-31","cited_by_count":79},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79},{"id":"2303.14341","title":"Towards Accurate Post-Training Quantization for Vision Transformer","created":"2023-03-25","cited_by_count":71},{"id":"2107.01378","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","created":"2021-07-03","cited_by_count":60},{"id":"1809.04570","title":"FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks","created":"2018-09-12","cited_by_count":56},{"id":"2103.09301","title":"Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers","created":"2021-03-16","cited_by_count":54},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46},{"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":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41},{"id":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41},{"id":"2208.05163","title":"Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization","created":"2022-08-10","cited_by_count":29},{"id":"2407.12951","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","created":"2024-07-17","cited_by_count":29},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20},{"id":"2304.03986","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","created":"2023-04-08","cited_by_count":18},{"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":"2104.12766","title":"HAO: Hardware-aware neural Architecture Optimization for Efficient Inference","created":"2021-04-26","cited_by_count":16},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16},{"id":"1802.09769","title":"L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks","created":"2018-02-27","cited_by_count":15},{"id":"2111.09499","title":"Dynamically pruning segformer for efficient semantic segmentation","created":"2021-11-18","cited_by_count":13},{"id":"2302.09108","title":"ViTA: A Vision Transformer Inference Accelerator for Edge Applications","created":"2023-02-17","cited_by_count":11},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8},{"id":"2207.06177","title":"RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment","created":"2022-07-13","cited_by_count":8},{"id":"2305.12901","title":"TSPTQ-ViT: Two-scaled post-training quantization for vision transformer","created":"2023-05-22","cited_by_count":7},{"id":"2402.09709","title":"ME-ViT: A Single-Load Memory-Efficient FPGA Accelerator for Vision Transformers","created":"2024-02-15","cited_by_count":7},{"id":"1512.04295","title":"Origami: A 803 GOp/s/W Convolutional Network Accelerator","created":"2015-12-14","cited_by_count":6},{"id":"2404.15185","title":"PIVOT- Input-aware Path Selection for Energy-efficient ViT Inference","created":"2024-04-10","cited_by_count":5},{"id":"2410.09324","title":"Token Pruning using a Lightweight Background Aware Vision Transformer","created":"2024-10-12","cited_by_count":3},{"id":"2106.05152","title":"Rethinking Transfer Learning for Medical Image Classification","created":"2021-06-09","cited_by_count":2}],"next_cursor":null}