{"total":35,"rows":[{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396,"area":null},{"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,"area":null},{"id":"2103.06877","title":"Fast and Accurate Model Scaling","created":"2021-03-11","cited_by_count":46,"area":null},{"id":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36,"area":null},{"id":"2112.09445","title":"Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation","created":"2021-12-17","cited_by_count":36,"area":null},{"id":"2106.13700","title":"ViTAS: Vision Transformer Architecture Search","created":"2021-06-25","cited_by_count":31,"area":null},{"id":"2102.10490","title":"Stronger NAS with Weaker Predictors","created":"2021-02-21","cited_by_count":28,"area":null},{"id":"2211.10526","title":"Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2103.14026","title":"AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks","created":"2021-03-25","cited_by_count":19,"area":null},{"id":"2103.07289","title":"Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator","created":"2021-03-12","cited_by_count":15,"area":null},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","cited_by_count":15,"area":null},{"id":"2204.04705","title":"SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems","created":"2022-04-10","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2105.09356","title":"Generative Adversarial Neural Architecture Search","created":"2021-05-19","cited_by_count":9,"area":null},{"id":"2105.03014","title":"BasisNet: Two-stage Model Synthesis for Efficient Inference","created":"2021-05-07","cited_by_count":7,"area":null},{"id":"2108.08189","title":"FOX-NAS: Fast, On-device and Explainable Neural Architecture Search","created":"2021-08-14","cited_by_count":7,"area":null},{"id":"2109.05765","title":"DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2211.01454","title":"Speeding up NAS with Adaptive Subset Selection","created":"2022-11-02","cited_by_count":6,"area":null},{"id":"2103.11833","title":"AutoSpace: Neural Architecture Search with Less Human Interference","created":"2021-03-22","cited_by_count":5,"area":null},{"id":"2107.03815","title":"Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2303.13121","title":"DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter","created":"2023-03-23","cited_by_count":5,"area":null},{"id":"2109.12426","title":"Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search","created":"2021-09-25","cited_by_count":4,"area":null},{"id":"2109.15273","title":"DAAS: Differentiable Architecture and Augmentation Policy Search","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2203.08399","title":"Privacy-preserving Online AutoML for Domain-Specific Face Detection","created":"2022-03-16","cited_by_count":4,"area":null},{"id":"2308.13173","title":"DISGO: Automatic End-to-End Evaluation for Scene Text OCR","created":"2023-08-25","cited_by_count":4,"area":null},{"id":"2301.04502","title":"Pruning Compact ConvNets for Efficient Inference","created":"2023-01-11","cited_by_count":2,"area":null},{"id":"2105.03176","title":"ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2203.08951","title":"Meta-Learning of NAS for Few-shot Learning in Medical Image Applications","created":"2022-03-16","cited_by_count":1,"area":null},{"id":"2406.00291","title":"Multi-Objective Neural Architecture Search by Learning Search Space Partitions","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2108.03001","title":"Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2207.05420","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2210.14460","title":"PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2402.04885","title":"A Unified Gaussian Process for Branching and Nested Hyperparameter Optimization","created":"2024-01-19","cited_by_count":0,"area":null}],"next_cursor":null}