{"total":179,"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":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42,"area":null},{"id":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41,"area":null},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41,"area":null},{"id":"2306.07713","title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","created":"2023-06-13","cited_by_count":31,"area":null},{"id":"2310.00927","title":"Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP","created":"2023-10-02","cited_by_count":26,"area":null},{"id":"2503.02891","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2309.01430","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","created":"2023-09-04","cited_by_count":21,"area":null},{"id":"2502.12677","title":"Spiking Vision Transformer with Saccadic Attention","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2302.14771","title":"Generic-to-Specific Distillation of Masked Autoencoders","created":"2023-02-28","cited_by_count":19,"area":null},{"id":"2408.03291","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","created":"2024-08-06","cited_by_count":19,"area":null},{"id":"2408.15235","title":"Learning-based Multi-View Stereo: A Survey","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2312.05760","title":"RepViT-SAM: Towards Real-Time Segmenting Anything","created":"2023-12-10","cited_by_count":17,"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":"2210.12333","title":"Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets","created":"2022-10-22","cited_by_count":15,"area":null},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"id":"2412.11892","title":"From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach","created":"2024-12-16","cited_by_count":15,"area":null},{"id":"2507.13364","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","created":"2025-07-06","cited_by_count":14,"area":null},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13,"area":null},{"id":"2307.07757","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","created":"2023-07-15","cited_by_count":13,"area":null},{"id":"2312.05614","title":"Transformer as Linear Expansion of Learngene","created":"2023-12-09","cited_by_count":13,"area":null},{"id":"2312.09059","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","created":"2023-12-14","cited_by_count":13,"area":null},{"id":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2308.12231","title":"SPPNet: A Single-Point Prompt Network for Nuclei Image Segmentation","created":"2023-08-23","cited_by_count":12,"area":null},{"id":"2309.16967","title":"nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance","created":"2023-09-29","cited_by_count":12,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2407.14153","title":"De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation","created":"2024-07-19","cited_by_count":11,"area":null},{"id":"2409.01184","title":"PitVis-2023 Challenge: Workflow Recognition in videos of Endoscopic Pituitary Surgery","created":"2024-09-02","cited_by_count":10,"area":null},{"id":"2403.09620","title":"PosSAM: Panoptic Open-vocabulary Segment Anything","created":"2024-03-14","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":"2310.05392","title":"Lightweight Full-Convolutional Siamese Tracker","created":"2023-10-09","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":"2403.06871","title":"On the Generalization Ability of Unsupervised Pretraining","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2402.19145","title":"A SAM-guided Two-stream Lightweight Model for Anomaly Detection","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2403.09195","title":"SAM-Lightening: A Lightweight Segment Anything Model with Dilated Flash Attention to Achieve 30 times Acceleration","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2410.23625","title":"EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography","created":"2024-10-31","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":"2305.11392","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2305.14974","title":"Block-local learning with probabilistic latent representations","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2505.04720","title":"False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims","created":"2025-05-07","cited_by_count":6,"area":null},{"id":"2509.08302","title":"Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2211.00218","title":"Pixel-Wise Contrastive Distillation","created":"2022-11-01","cited_by_count":5,"area":null},{"id":"2303.14778","title":"RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning","created":"2023-03-26","cited_by_count":5,"area":null},{"id":"2304.02263","title":"Towards Efficient Task-Driven Model Reprogramming with Foundation Models","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2403.06138","title":"BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification","created":"2024-03-10","cited_by_count":5,"area":null},{"id":"2404.09259","title":"FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity","created":"2024-04-14","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":"2505.21847","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2507.02748","title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2511.15771","title":"UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2603.04731","title":"When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","cited_by_count":4,"area":null},{"id":"2402.06004","title":"Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2412.16085","title":"Efficient MedSAMs: Segment Anything in Medical Images on Laptop","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2502.08227","title":"Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2505.23961","title":"MangoLeafViT: Leveraging Lightweight Vision Transformer with Runtime Augmentation for Efficient Mango Leaf Disease Classification","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2506.07847","title":"F2Net: A Frequency-Fused Network for Ultra-High Resolution Remote Sensing Segmentation","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2511.15833","title":"EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3","created":"2025-11-19","cited_by_count":4,"area":null},{"id":"2308.06548","title":"Revisiting Vision Transformer from the View of Path Ensemble","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2311.03912","title":"FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer","created":"2023-11-07","cited_by_count":3,"area":null},{"id":"2402.11305","title":"On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2406.19391","title":"Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2407.04400","title":"Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2412.16553","title":"Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2503.16659","title":"Advances in Protein Representation Learning: Methods, Applications, and Future Directions","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2504.02351","title":"Agglomerating Large Vision Encoders via Distillation for VFSS Segmentation","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2504.02440","title":"HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2504.09326","title":"Infused Suppression Of Magnification Artefacts For Micro-AU Detection","created":"2025-04-12","cited_by_count":3,"area":null},{"id":"2506.03110","title":"Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2506.18072","title":"Multimodal Medical Image Binding via Shared Text Embeddings","created":"2025-06-22","cited_by_count":3,"area":null},{"id":"2507.09562","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2602.00334","title":"Adaptive Momentum and Nonlinear Damping for Neural Network Training","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2303.00501","title":"OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2305.12796","title":"Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2311.03149","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2404.00509","title":"DailyMAE: Towards Pretraining Masked Autoencoders in One Day","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2404.02544","title":"Semi-Supervised Unconstrained Head Pose Estimation in the Wild","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2409.14784","title":"SAMEdge: An Edge-cloud Video Analytics Architecture for the Segment Anything Model","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2410.17661","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2502.02763","title":"Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2502.03907","title":"No Free Lunch in Annotation either: An objective evaluation of foundation models for streamlining annotation in animal tracking","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2502.19513","title":"Mixtraining: A Better Trade-Off Between Compute and Performance","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2503.08201","title":"Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.10632","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.06118","title":"The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2507.08710","title":"L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2507.14481","title":"DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2509.01433","title":"Temporal Representation Learning for Real-Time Ultrasound Analysis","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2509.13255","title":"ResidualViT for Efficient Temporally Dense Video Encoding","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2511.20359","title":"From Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations","created":"2025-11-25","cited_by_count":2,"area":null}],"next_cursor":"100"}