{"total":45,"rows":[{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109,"area":null},{"id":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89,"area":null},{"id":"2204.05525","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","created":"2022-04-12","cited_by_count":82,"area":null},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55,"area":null},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"area":null},{"id":"2307.01838","title":"EdgeFace: Efficient Face Recognition Model for Edge Devices","created":"2023-07-04","cited_by_count":33,"area":null},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31,"area":null},{"id":"2108.05894","title":"MicroNet: Improving Image Recognition with Extremely Low FLOPs","created":"2021-08-12","cited_by_count":26,"area":null},{"id":"2105.10533","title":"BCNet: Searching for Network Width with Bilaterally Coupled Network","created":"2021-05-21","cited_by_count":23,"area":null},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2103.03081","title":"An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works","created":"2021-02-24","cited_by_count":13,"area":null},{"id":"2205.12635","title":"MoCoViT: Mobile Convolutional Vision Transformer","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2303.13097","title":"CP$^3$: Channel Pruning Plug-in for Point-based Networks","created":"2023-03-23","cited_by_count":10,"area":null},{"id":"2311.03747","title":"SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2403.19490","title":"Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2101.08525","title":"GhostSR: Learning Ghost Features for Efficient Image Super-Resolution","created":"2021-01-21","cited_by_count":8,"area":null},{"id":"2203.03324","title":"Dynamic ConvNets on Tiny Devices via Nested Sparsity","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2306.06365","title":"FalconNet: Factorization for the Light-weight ConvNets","created":"2023-06-10","cited_by_count":6,"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":"2307.13901","title":"YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems","created":"2023-07-26","cited_by_count":5,"area":null},{"id":"2504.19646","title":"xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devices","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2203.13714","title":"Searching for Network Width with Bilaterally Coupled Network","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2207.07267","title":"ScaleNet: Searching for the Model to Scale","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2301.10750","title":"Out of Distribution Performance of State of Art Vision Model","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2308.03821","title":"Distributionally Robust Classification on a Data Budget","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2403.13839","title":"depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2605.04769","title":"Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2102.03987","title":"Deep Learning Based Walking Tasks Classification in Older Adults using fNIRS","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2109.00170","title":"Architecture Aware Latency Constrained Sparse Neural Networks","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2305.03058","title":"Plug-and-Play Multilingual Few-shot Spoken Words Recognition","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2406.04820","title":"Navigating Efficiency in MobileViT through Gaussian Process on Global Architecture Factors","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2410.22709","title":"FilterViT and DropoutViT","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2501.11919","title":"Improving Fine-Tuning with Latent Cluster Correction","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2507.12105","title":"Out-of-distribution data supervision towards biomedical semantic segmentation","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2512.07391","title":"GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring","created":"2025-12-08","cited_by_count":0,"area":null}],"next_cursor":null}