{"total":206,"rows":[{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352,"area":null},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188,"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":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"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":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2303.15446","title":"SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications","created":"2023-03-27","cited_by_count":66,"area":null},{"id":"2207.05501","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","created":"2022-07-12","cited_by_count":65,"area":null},{"id":"2306.06189","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","created":"2023-06-09","cited_by_count":65,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"area":null},{"id":"2307.08579","title":"Scale-Aware Modulation Meet Transformer","created":"2023-07-17","cited_by_count":49,"area":null},{"id":"2212.08057","title":"Real-Time Neural Light Field on Mobile Devices","created":"2022-12-15","cited_by_count":48,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2301.01146","title":"Rethinking Mobile Block for Efficient Attention-based Models","created":"2023-01-03","cited_by_count":36,"area":null},{"id":"2307.00395","title":"MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications","created":"2023-07-01","cited_by_count":35,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2306.11248","title":"Dynamic Perceiver for Efficient Visual Recognition","created":"2023-06-20","cited_by_count":33,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","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":"2306.00396","title":"Lightweight Vision Transformer with Bidirectional Interaction","created":"2023-06-01","cited_by_count":25,"area":null},{"id":"2211.12735","title":"Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration","created":"2022-11-23","cited_by_count":24,"area":null},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24,"area":null},{"id":"2302.13372","title":"Localizing Moments in Long Video Via Multimodal Guidance","created":"2023-02-26","cited_by_count":23,"area":null},{"id":"2503.06625","title":"Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking","created":"2025-03-09","cited_by_count":23,"area":null},{"id":"2310.19380","title":"TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition","created":"2023-10-30","cited_by_count":21,"area":null},{"id":"2405.06849","title":"GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2407.04616","title":"Isomorphic Pruning for Vision Models","created":"2024-07-05","cited_by_count":21,"area":null},{"id":"2210.09223","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","created":"2022-10-14","cited_by_count":20,"area":null},{"id":"2403.17909","title":"ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection","created":"2024-03-26","cited_by_count":19,"area":null},{"id":"2211.16421","title":"RGB no more: Minimally-decoded JPEG Vision Transformers","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2301.13156","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17,"area":null},{"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,"area":null},{"id":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17,"area":null},{"id":"2307.07102","title":"Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar","created":"2023-07-14","cited_by_count":16,"area":null},{"id":"2310.06522","title":"Watt For What: Rethinking Deep Learning's Energy-Performance Relationship","created":"2023-10-10","cited_by_count":16,"area":null},{"id":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2305.17235","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","created":"2023-05-26","cited_by_count":14,"area":null},{"id":"2407.17261","title":"Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation","created":"2024-07-24","cited_by_count":14,"area":null},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2407.04208","title":"AMD: Automatic Multi-step Distillation of Large-scale Vision Models","created":"2024-07-05","cited_by_count":12,"area":null},{"id":"2408.03703","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","created":"2024-08-07","cited_by_count":12,"area":null},{"id":"2408.07576","title":"MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation","created":"2024-08-14","cited_by_count":12,"area":null},{"id":"2408.12568","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2303.09730","title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2308.06693","title":"Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation","created":"2023-08-13","cited_by_count":10,"area":null},{"id":"2507.01182","title":"Rapid Salient Object Detection with Difference Convolutional Neural Networks","created":"2025-07-01","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":"2406.05850","title":"Scaling Graph Convolutions for Mobile Vision","created":"2024-06-09","cited_by_count":9,"area":null},{"id":"2501.06357","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2501.15369","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2303.06530","title":"Making Batch Normalization Great in Federated Deep Learning","created":"2023-03-12","cited_by_count":8,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","cited_by_count":8,"area":null},{"id":"2211.07198","title":"Fcaformer: Forward Cross Attention in Hybrid Vision Transformer","created":"2022-11-14","cited_by_count":7,"area":null},{"id":"2312.05743","title":"Building Variable-sized Models via Learngene Pool","created":"2023-12-10","cited_by_count":7,"area":null},{"id":"2404.07217","title":"Attention-aware Semantic Communications for Collaborative Inference","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2501.16811","title":"Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2303.12557","title":"Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems","created":"2023-03-22","cited_by_count":6,"area":null},{"id":"2304.05152","title":"PP-MobileSeg: Explore the Fast and Accurate Semantic Segmentation Model on Mobile Devices","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2308.02794","title":"Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution","created":"2023-08-05","cited_by_count":6,"area":null},{"id":"2308.05235","title":"Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover Mapping","created":"2023-08-09","cited_by_count":6,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2406.06136","title":"A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2408.01708","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","created":"2024-08-03","cited_by_count":6,"area":null},{"id":"2409.03460","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2303.17803","title":"Rethinking Local Perception in Lightweight Vision Transformer","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2304.03481","title":"PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift","created":"2023-04-07","cited_by_count":5,"area":null},{"id":"2308.04397","title":"LEFormer: A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagery","created":"2023-08-08","cited_by_count":5,"area":null},{"id":"2312.08614","title":"Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost","created":"2023-12-14","cited_by_count":5,"area":null},{"id":"2404.11630","title":"SNP: Structured Neuron-level Pruning to Preserve Attention Scores","created":"2024-04-18","cited_by_count":5,"area":null},{"id":"2407.08965","title":"Lite-SAM Is Actually What You Need for Segment Everything","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2407.11306","title":"PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2407.12067","title":"MaskVD: Region Masking for Efficient Video Object Detection","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2411.04967","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2507.05193","title":"RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2508.08811","title":"Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment","created":"2025-08-12","cited_by_count":5,"area":null},{"id":"2211.07157","title":"ParCNetV2: Oversized Kernel with Enhanced Attention","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2403.07246","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2406.08816","title":"ToSA: Token Selective Attention for Efficient Vision Transformers","created":"2024-06-13","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":"2412.00348","title":"Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2502.15021","title":"Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2505.22342","title":"Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2604.19196","title":"Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2208.12257","title":"Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2210.15943","title":"Grafting Vision Transformers","created":"2022-10-28","cited_by_count":3,"area":null}],"next_cursor":"100"}