{"total":108,"rows":[{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135,"area":null},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642,"area":null},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289,"area":null},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241,"area":null},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199,"area":null},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146,"area":"ssm"},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2304.10970","title":"Can GPT-4 Perform Neural Architecture Search?","created":"2023-04-21","cited_by_count":74,"area":null},{"id":"2304.09224","title":"Quantum machine learning for image classification","created":"2023-04-18","cited_by_count":57,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2404.13671","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","created":"2024-04-21","cited_by_count":51,"area":null},{"id":"2307.08579","title":"Scale-Aware Modulation Meet Transformer","created":"2023-07-17","cited_by_count":49,"area":null},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39,"area":null},{"id":"2109.03144","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2107.13046","title":"MixFaceNets: Extremely Efficient Face Recognition Networks","created":"2021-07-27","cited_by_count":36,"area":null},{"id":"2108.10710","title":"PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation","created":"2021-08-24","cited_by_count":36,"area":"distill"},{"id":"2103.08756","title":"Revisiting Dynamic Convolution via Matrix Decomposition","created":"2021-03-15","cited_by_count":35,"area":null},{"id":"2412.16986","title":"Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection","created":"2024-12-22","cited_by_count":34,"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":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28,"area":null},{"id":"2212.11005","title":"Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective","created":"2022-12-21","cited_by_count":28,"area":null},{"id":"2109.15099","title":"PP-LCNet: A Lightweight CPU Convolutional Neural Network","created":"2021-09-17","cited_by_count":27,"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":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2310.17653","title":"Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2206.10526","title":"QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization","created":"2022-06-21","cited_by_count":18,"area":null},{"id":"2211.11747","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","created":"2022-11-15","cited_by_count":18,"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":"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":"2404.11202","title":"GhostNetV3: Exploring the Training Strategies for Compact Models","created":"2024-04-17","cited_by_count":14,"area":null},{"id":"2104.00031","title":"NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization","created":"2021-03-31","cited_by_count":13,"area":null},{"id":"2104.00597","title":"One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking","created":"2021-04-01","cited_by_count":12,"area":null},{"id":"2105.12053","title":"Real-time Monocular Depth Estimation with Sparse Supervision on Mobile","created":"2021-05-25","cited_by_count":12,"area":null},{"id":"2111.12609","title":"GreedyNASv2: Greedier Search with a Greedy Path Filter","created":"2021-11-24","cited_by_count":12,"area":null},{"id":"2202.07242","title":"Neural Architecture Search for Dense Prediction Tasks in Computer Vision","created":"2022-02-15","cited_by_count":12,"area":null},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2205.12635","title":"MoCoViT: Mobile Convolutional Vision Transformer","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2105.10559","title":"Hyper-Convolution Networks for Biomedical Image Segmentation","created":"2021-05-21","cited_by_count":10,"area":null},{"id":"2204.10762","title":"Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation","created":"2022-04-22","cited_by_count":10,"area":null},{"id":"2308.14852","title":"SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data","created":"2023-08-28","cited_by_count":9,"area":"distill"},{"id":"2501.10067","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","created":"2025-01-17","cited_by_count":8,"area":null},{"id":"2301.06393","title":"$\\beta$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search","created":"2023-01-16","cited_by_count":7,"area":null},{"id":"2308.04168","title":"EFaR 2023: Efficient Face Recognition Competition","created":"2023-08-08","cited_by_count":7,"area":null},{"id":"2407.15219","title":"Efficient Visual Transformer by Learnable Token Merging","created":"2024-07-21","cited_by_count":7,"area":"inference"},{"id":"2306.06365","title":"FalconNet: Factorization for the Light-weight ConvNets","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2311.11587","title":"LDConv: Linear deformable convolution for improving convolutional neural networks","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2401.14469","title":"Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2406.07879","title":"KernelWarehouse: Rethinking the Design of Dynamic Convolution","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2408.01690","title":"IDNet: A Novel Dataset for Identity Document Analysis and Fraud Detection","created":"2024-08-03","cited_by_count":6,"area":null},{"id":"2509.26037","title":"CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search","created":"2025-09-30","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":"2405.20838","title":"einspace: Searching for Neural Architectures from Fundamental Operations","created":"2024-05-31","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":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2212.13970","title":"Breaking the Architecture Barrier: A Method for Efficient Knowledge Transfer Across Networks","created":"2022-12-28","cited_by_count":4,"area":null},{"id":"2403.01326","title":"DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2210.17180","title":"Automated Dominative Subspace Mining for Efficient Neural Architecture Search","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2405.18302","title":"Deep Network Pruning: A Comparative Study on CNNs in Face Recognition","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2111.00775","title":"PP-ShiTu: A Practical Lightweight Image Recognition System","created":"2021-11-01","cited_by_count":2,"area":null},{"id":"2202.02701","title":"Hyper-Convolutions via Implicit Kernels for Medical Imaging","created":"2022-02-06","cited_by_count":2,"area":null},{"id":"2208.04246","title":"Snowpack Estimation in Key Mountainous Water Basins from Openly-Available, Multimodal Data Sources","created":"2022-08-08","cited_by_count":2,"area":null},{"id":"2304.07254","title":"Dynamic Mobile-Former: Strengthening Dynamic Convolution with Attention and Residual Connection in Kernel Space","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2307.09120","title":"Light-Weight Vision Transformer with Parallel Local and Global Self-Attention","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2307.10697","title":"SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2312.14200","title":"Efficient Architecture Search via Bi-level Data Pruning","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2407.15600","title":"A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2412.08763","title":"Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI","created":"2024-12-11","cited_by_count":2,"area":null},{"id":"2505.04397","title":"PURe: A Plug-and-Play Product-Unit Residual Module for Vision Networks","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2508.09824","title":"Reverse Convolution and Its Applications to Image Restoration","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2102.05368","title":"RoBIC: A benchmark suite for assessing classifiers robustness","created":"2021-02-10","cited_by_count":1,"area":null},{"id":"2104.14125","title":"Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions","created":"2021-04-29","cited_by_count":1,"area":null},{"id":"2107.11170","title":"Bias Loss for Mobile Neural Networks","created":"2021-07-23","cited_by_count":1,"area":null},{"id":"2205.09678","title":"Semi-Supervised Learning for Image Classification using Compact Networks in the BioMedical Context","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2209.07738","title":"DMFormer: Closing the Gap Between CNN and Vision Transformers","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2301.10038","title":"Progressive Meta-Pooling Learning for Lightweight Image Classification Model","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2301.13514","title":"Fourier Sensitivity and Regularization of Computer Vision Models","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2403.07035","title":"Multiple Population Alternate Evolution Neural Architecture Search","created":"2024-03-11","cited_by_count":1,"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":"2406.00291","title":"Multi-Objective Neural Architecture Search by Learning Search Space Partitions","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2412.00724","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","created":"2024-12-01","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":"2605.17470","title":"EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2204.06697","title":"HASA: Hybrid Architecture Search with Aggregation Strategy for Echinococcosis Classification and Ovary Segmentation in Ultrasound Images","created":"2022-04-14","cited_by_count":0,"area":null},{"id":"2205.10515","title":"Visualizing CoAtNet Predictions for Aiding Melanoma Detection","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2209.10327","title":"SDA-$x$Net: Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2210.17141","title":"Studying inductive biases in image classification task","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2212.08448","title":"From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search","created":"2022-12-16","cited_by_count":0,"area":null},{"id":"2305.09924","title":"CageViT: Convolutional Activation Guided Efficient Vision Transformer","created":"2023-05-17","cited_by_count":0,"area":null}],"next_cursor":"100"}