{"list":"other","total":71,"rows":[{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"1906.06310","title":"Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving","created":"2019-06-14","cited_by_count":188},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180},{"id":"2203.01502","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","created":"2022-03-03","cited_by_count":153},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"1806.03884","title":"Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis","created":"2018-06-11","cited_by_count":146},{"id":"1706.03662","title":"Practical Gauss-Newton Optimisation for Deep Learning","created":"2017-06-12","cited_by_count":142},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137},{"id":"1812.11941","title":"High Quality Monocular Depth Estimation via Transfer Learning","created":"2018-12-31","cited_by_count":133},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"2002.10941","title":"A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation","created":"2020-02-22","cited_by_count":101},{"id":"1905.05934","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","created":"2019-05-15","cited_by_count":98},{"id":"1903.03273","title":"FastDepth: Fast Monocular Depth Estimation on Embedded Systems","created":"2019-03-08","cited_by_count":94},{"id":"2303.14341","title":"Towards Accurate Post-Training Quantization for Vision Transformer","created":"2023-03-25","cited_by_count":71},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56},{"id":"2210.09670","title":"Hierarchical Normalization for Robust Monocular Depth Estimation","created":"2022-10-18","cited_by_count":52},{"id":"1903.04202","title":"Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation","created":"2019-03-11","cited_by_count":49},{"id":"2103.04216","title":"Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction","created":"2021-03-07","cited_by_count":48},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42},{"id":"2208.13241","title":"Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image","created":"2022-08-28","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":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2108.08910","title":"Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search","created":"2021-08-18","cited_by_count":34},{"id":"2312.05693","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","created":"2023-12-09","cited_by_count":33},{"id":"2206.01198","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","created":"2022-06-02","cited_by_count":32},{"id":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","cited_by_count":25},{"id":"2302.14705","title":"AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers","created":"2023-02-28","cited_by_count":24},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20},{"id":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16},{"id":"2410.14725","title":"Rethinking Token Reduction for State Space Models","created":"2024-10-16","cited_by_count":15},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14},{"id":"2411.01171","title":"Fast and Memory-Efficient Video Diffusion Using Streamlined Inference","created":"2024-11-02","cited_by_count":14},{"id":"2403.10799","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","created":"2024-03-16","cited_by_count":13},{"id":"2208.05066","title":"The Relative Importance of Depth Cues and Semantic Edges for Indoor Mobility Using Simulated Prosthetic Vision in Immersive Virtual Reality","created":"2022-08-09","cited_by_count":10},{"id":"2308.10569","title":"Real-time Monocular Depth Estimation on Embedded Systems","created":"2023-08-21","cited_by_count":6},{"id":"2412.06845","title":"7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement","created":"2024-12-08","cited_by_count":5},{"id":"1905.05212","title":"Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning","created":"2019-05-13","cited_by_count":4},{"id":"2408.05363","title":"AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge","created":"2024-07-25","cited_by_count":1}],"next_cursor":null}