{"total":122,"rows":[{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"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":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2208.07791","title":"Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model","created":"2022-08-16","cited_by_count":58,"area":"diffusion"},{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2205.15463","title":"Few-Shot Diffusion Models","created":"2022-05-30","cited_by_count":38,"area":"diffusion"},{"id":"2212.00932","title":"ObjectStitch: Generative Object Compositing","created":"2022-12-02","cited_by_count":36,"area":null},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"area":null},{"id":"2210.05958","title":"Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets","created":"2022-10-12","cited_by_count":29,"area":null},{"id":"2302.03751","title":"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective","created":"2023-02-07","cited_by_count":28,"area":null},{"id":"2209.15190","title":"Neural Integral Equations","created":"2022-09-30","cited_by_count":23,"area":null},{"id":"2303.15466","title":"Supervised Masked Knowledge Distillation for Few-Shot Transformers","created":"2023-03-25","cited_by_count":23,"area":"distill"},{"id":"2202.04996","title":"AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks","created":"2022-02-10","cited_by_count":22,"area":null},{"id":"2211.10686","title":"Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network","created":"2022-11-19","cited_by_count":19,"area":null},{"id":"2306.06635","title":"2-D SSM: A General Spatial Layer for Visual Transformers","created":"2023-06-11","cited_by_count":18,"area":null},{"id":"2405.18144","title":"4-bit Shampoo for Memory-Efficient Network Training","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2310.20704","title":"Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders","created":"2023-10-31","cited_by_count":17,"area":null},{"id":"2210.00944","title":"Attention Distillation: self-supervised vision transformer students need more guidance","created":"2022-10-03","cited_by_count":16,"area":"distill"},{"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":"2211.11393","title":"TFormer: A throughout fusion transformer for multi-modal skin lesion diagnosis","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2208.14558","title":"Augraphy: A Data Augmentation Library for Document Images","created":"2022-08-30","cited_by_count":14,"area":null},{"id":"2308.12532","title":"FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2205.10660","title":"Vision Transformers in 2022: An Update on Tiny ImageNet","created":"2022-05-21","cited_by_count":13,"area":null},{"id":"2205.14794","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","created":"2022-05-30","cited_by_count":13,"area":null},{"id":"2306.12054","title":"A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Staging","created":"2023-06-21","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2403.10519","title":"Frozen Feature Augmentation for Few-Shot Image Classification","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2308.06093","title":"Experts Weights Averaging: A New General Training Scheme for Vision Transformers","created":"2023-08-11","cited_by_count":12,"area":"moe"},{"id":"2312.06733","title":"TULIP: Transformer for Upsampling of LiDAR Point Clouds","created":"2023-12-11","cited_by_count":12,"area":null},{"id":"2204.08043","title":"Continual Hippocampus Segmentation with Transformers","created":"2022-04-17","cited_by_count":11,"area":null},{"id":"2303.04721","title":"Fast offset corrected in-memory training","created":"2023-03-08","cited_by_count":11,"area":null},{"id":"2301.11722","title":"Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?","created":"2023-01-27","cited_by_count":10,"area":"diffusion"},{"id":"2409.03367","title":"TBConvL-Net: A Hybrid Deep Learning Architecture for Robust Medical Image Segmentation","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2207.08148","title":"Improving Deep Neural Network Random Initialization Through Neuronal Rewiring","created":"2022-07-17","cited_by_count":7,"area":null},{"id":"2208.07216","title":"Class-attention Video Transformer for Engagement Intensity Prediction","created":"2022-08-12","cited_by_count":7,"area":null},{"id":"2210.08031","title":"Neural Attentive Circuits","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2211.05187","title":"Training a Vision Transformer from scratch in less than 24 hours with 1 GPU","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2302.03023","title":"V1T: large-scale mouse V1 response prediction using a Vision Transformer","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2304.05350","title":"Astroformer: More Data Might not be all you need for Classification","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2306.02090","title":"Deep Classifier Mimicry without Data Access","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2404.09326","title":"Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers","created":"2024-04-14","cited_by_count":6,"area":"distill"},{"id":"2408.14131","title":"GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2402.17863","title":"Vision Transformers with Natural Language Semantics","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2212.14215","title":"Local Learning on Transformers via Feature Reconstruction","created":"2022-12-29","cited_by_count":4,"area":null},{"id":"2308.08339","title":"Denoising Diffusion Probabilistic Model for Retinal Image Generation and Segmentation","created":"2023-08-16","cited_by_count":4,"area":"diffusion"},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2402.01863","title":"DFML: Decentralized Federated Mutual Learning","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2404.01139","title":"Structured Initialization for Attention in Vision Transformers","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2505.08259","title":"CNN and ViT Efficiency Study on Tiny ImageNet and DermaMNIST Datasets","created":"2025-05-13","cited_by_count":4,"area":null},{"id":"2509.16391","title":"CoUn: Empowering Machine Unlearning via Contrastive Learning","created":"2025-09-19","cited_by_count":4,"area":"safety"},{"id":"2204.05566","title":"Compact Model Training by Low-Rank Projection with Energy Transfer","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2305.07102","title":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2308.13772","title":"Boosting Residual Networks with Group Knowledge","created":"2023-08-26","cited_by_count":3,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2312.06940","title":"Benchmarking Deep Learning Classifiers for SAR Automatic Target Recognition","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2404.19579","title":"Automatic Cardiac Pathology Recognition in Echocardiography Images Using Higher Order Dynamic Mode Decomposition and a Vision Transformer for Small Datasets","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2408.11351","title":"Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodes","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2409.19582","title":"Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2509.08959","title":"CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2205.14477","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","created":"2022-05-28","cited_by_count":2,"area":null},{"id":"2210.01177","title":"Introducing Vision Transformer for Alzheimer's Disease classification task with 3D input","created":"2022-10-03","cited_by_count":2,"area":null},{"id":"2307.05616","title":"Image Reconstruction using Enhanced Vision Transformer","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2402.00564","title":"A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2403.06417","title":"Enhanced Sparsification via Stimulative Training","created":"2024-03-11","cited_by_count":2,"area":"distill"},{"id":"2403.18593","title":"Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2405.08621","title":"RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2407.13920","title":"DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2410.04801","title":"Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.12025","title":"Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2410.21958","title":"Spatio-temporal Transformers for Action Unit Classification with Event Cameras","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2506.15588","title":"Memory-Efficient Differentially Private Training with Gradient Random Projection","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2210.14319","title":"Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2212.05677","title":"Masked autoencoders are effective solution to transformer data-hungry","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2309.05375","title":"Toward a Deeper Understanding: RetNet Viewed through Convolution","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2309.08129","title":"Increasing diversity of omni-directional images generated from single image using cGAN based on MLPMixer","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2403.15517","title":"Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2404.04527","title":"VTR: An Optimized Vision Transformer for SAR ATR Acceleration on FPGA","created":"2024-04-06","cited_by_count":1,"area":null},{"id":"2408.15305","title":"Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis","created":"2024-08-27","cited_by_count":1,"area":"moe"},{"id":"2409.09984","title":"Convergence of Sharpness-Aware Minimization Algorithms using Increasing Batch Size and Decaying Learning Rate","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2410.08826","title":"Towards virtual painting recolouring using Vision Transformer on X-Ray Fluorescence datacubes","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2504.00564","title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.09265","title":"Mixture of Group Experts for Learning Invariant Representations","created":"2025-04-12","cited_by_count":1,"area":"moe"},{"id":"2510.23241","title":"Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2511.01292","title":"Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2512.13083","title":"DiRe: Diversity-promoting Regularization for Dataset Condensation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2205.08585","title":"CV4Code: Sourcecode Understanding via Visual Code Representations","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2304.01962","title":"Ethylene Leak Detection Based on Infrared Imaging: A Benchmark","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2304.02931","title":"Mask Detection and Classification in Thermal Face Images","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2305.16823","title":"HUB: Guiding Learned Optimizers with Continuous Prompt Tuning","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2307.13865","title":"Pretrained Deep 2.5D Models for Efficient Predictive Modeling from Retinal OCT","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2310.00369","title":"LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression","created":"2023-09-30","cited_by_count":0,"area":null},{"id":"2401.02656","title":"GTA: Guided Transfer of Spatial Attention from Object-Centric Representations","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2404.00107","title":"Robust Ensemble Person Re-Identification via Orthogonal Fusion with Occlusion Handling","created":"2024-03-29","cited_by_count":0,"area":null},{"id":"2408.11433","title":"Towards Aligned Data Removal via Twin Machine Unlearning","created":"2024-08-21","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}