{"total":572,"rows":[{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2106.11170","title":"Transformer-based Spatial-Temporal Feature Learning for EEG Decoding","created":"2021-06-11","cited_by_count":97,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2210.10239","title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","created":"2022-10-19","cited_by_count":93,"area":null},{"id":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75,"area":null},{"id":"2105.10490","title":"Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection","created":"2021-05-21","cited_by_count":68,"area":null},{"id":"2110.08059","title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","created":"2021-10-15","cited_by_count":66,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2311.18297","title":"TrustMark: Universal Watermarking for Arbitrary Resolution Images","created":"2023-11-30","cited_by_count":51,"area":null},{"id":"2101.06116","title":"Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects","created":"2021-01-15","cited_by_count":49,"area":null},{"id":"2203.13834","title":"A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration","created":"2022-03-25","cited_by_count":49,"area":null},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46,"area":null},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46,"area":null},{"id":"2304.02786","title":"UNICORN: A Unified Backdoor Trigger Inversion Framework","created":"2023-04-05","cited_by_count":46,"area":null},{"id":"2402.03526","title":"nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model","created":"2024-02-05","cited_by_count":45,"area":null},{"id":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2104.00905","title":"Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation","created":"2021-04-02","cited_by_count":41,"area":null},{"id":"2106.09895","title":"PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2201.12738","title":"AutoSNN: Towards Energy-Efficient Spiking Neural Networks","created":"2022-01-30","cited_by_count":40,"area":null},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40,"area":null},{"id":"2202.06382","title":"Training with More Confidence: Mitigating Injected and Natural Backdoors During Training","created":"2022-02-13","cited_by_count":38,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2207.13159","title":"TINYCD: A (Not So) Deep Learning Model For Change Detection","created":"2022-07-26","cited_by_count":36,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2203.15216","title":"Affine Medical Image Registration with Coarse-to-Fine Vision Transformer","created":"2022-03-29","cited_by_count":35,"area":null},{"id":"2303.04145","title":"Benign Overfitting for Two-layer ReLU Convolutional Neural Networks","created":"2023-03-07","cited_by_count":34,"area":null},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"area":null},{"id":"2305.13665","title":"Dual Focal Loss for Calibration","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2211.11838","title":"AdaFocal: Calibration-aware Adaptive Focal Loss","created":"2022-11-21","cited_by_count":32,"area":null},{"id":"2106.09613","title":"Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error","created":"2021-06-17","cited_by_count":29,"area":null},{"id":"2105.04286","title":"Primitive Representation Learning for Scene Text Recognition","created":"2021-05-10","cited_by_count":28,"area":null},{"id":"2112.01732","title":"MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection","created":"2021-12-03","cited_by_count":27,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2306.05524","title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2101.00440","title":"Refining activation downsampling with SoftPool","created":"2021-01-02","cited_by_count":26,"area":null},{"id":"2106.03412","title":"Resolution learning in deep convolutional networks using scale-space theory","created":"2021-06-07","cited_by_count":26,"area":null},{"id":"2106.16028","title":"Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network","created":"2021-06-30","cited_by_count":26,"area":null},{"id":"2109.07069","title":"F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2201.08673","title":"Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking","created":"2022-01-21","cited_by_count":26,"area":null},{"id":"2309.01083","title":"Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning","created":"2023-09-03","cited_by_count":26,"area":null},{"id":"2104.04569","title":"Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling","created":"2021-04-09","cited_by_count":25,"area":null},{"id":"2204.00220","title":"Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization","created":"2022-04-01","cited_by_count":25,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2112.05291","title":"LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization","created":"2021-12-10","cited_by_count":24,"area":null},{"id":"2201.12354","title":"Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning","created":"2022-01-28","cited_by_count":24,"area":null},{"id":"2203.16219","title":"Acknowledging the Unknown for Multi-label Learning with Single Positive Labels","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2211.07377","title":"Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing","created":"2022-11-14","cited_by_count":24,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2401.09323","title":"BENO: Boundary-embedded Neural Operators for Elliptic PDEs","created":"2024-01-17","cited_by_count":24,"area":null},{"id":"2208.03608","title":"Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value","created":"2022-08-07","cited_by_count":23,"area":null},{"id":"2104.01353","title":"Deepfake Detection Scheme Based on Vision Transformer and Distillation","created":"2021-04-03","cited_by_count":22,"area":null},{"id":"2107.09507","title":"EEG-based Cross-Subject Driver Drowsiness Recognition with an Interpretable Convolutional Neural Network","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2110.13059","title":"Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups","created":"2021-10-25","cited_by_count":22,"area":null},{"id":"2412.20665","title":"SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection","created":"2024-12-30","cited_by_count":22,"area":null},{"id":"2106.11593","title":"A Vertical Federated Learning Framework for Graph Convolutional Network","created":"2021-06-22","cited_by_count":21,"area":null},{"id":"2403.00849","title":"NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functions","created":"2024-02-29","cited_by_count":21,"area":null},{"id":"2501.05453","title":"An Empirical Study of Autoregressive Pre-training from Videos","created":"2025-01-09","cited_by_count":21,"area":null},{"id":"2203.14804","title":"Partially Does It: Towards Scene-Level FG-SBIR with Partial Input","created":"2022-03-28","cited_by_count":20,"area":null},{"id":"2202.04812","title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2312.14474","title":"MonoLSS: Learnable Sample Selection For Monocular 3D Detection","created":"2023-12-22","cited_by_count":19,"area":null},{"id":"2103.13549","title":"An evidential classifier based on Dempster-Shafer theory and deep learning","created":"2021-03-25","cited_by_count":18,"area":null},{"id":"2104.14006","title":"EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion","created":"2021-04-28","cited_by_count":18,"area":null},{"id":"2210.08001","title":"Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2308.14113","title":"Semantic-aware Consistency Network for Cloth-changing Person Re-Identification","created":"2023-08-27","cited_by_count":18,"area":null},{"id":"2102.00272","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","created":"2021-01-30","cited_by_count":17,"area":null},{"id":"2103.01319","title":"Adversarial training in communication constrained federated learning","created":"2021-03-01","cited_by_count":17,"area":null},{"id":"2106.10414","title":"Deep Learning for Functional Data Analysis with Adaptive Basis Layers","created":"2021-06-19","cited_by_count":17,"area":null},{"id":"2211.03796","title":"Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy","created":"2022-11-07","cited_by_count":17,"area":null},{"id":"2101.10932","title":"EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification","created":"2021-01-24","cited_by_count":16,"area":null},{"id":"2203.01714","title":"Weakly Supervised Object Localization as Domain Adaption","created":"2022-03-03","cited_by_count":16,"area":null},{"id":"2204.11188","title":"M2N: Mesh Movement Networks for PDE Solvers","created":"2022-04-24","cited_by_count":16,"area":null},{"id":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2305.16316","title":"Making Vision Transformers Truly Shift-Equivariant","created":"2023-05-25","cited_by_count":16,"area":null},{"id":"2309.06891","title":"Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?","created":"2023-09-13","cited_by_count":16,"area":null},{"id":"2401.16677","title":"T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives","created":"2024-01-30","cited_by_count":16,"area":null},{"id":"2206.08016","title":"Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2407.10159","title":"RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation","created":"2024-07-14","cited_by_count":15,"area":null},{"id":"2103.14793","title":"CalibDNN: Multimodal Sensor Calibration for Perception Using Deep Neural Networks","created":"2021-03-27","cited_by_count":14,"area":null},{"id":"2104.06279","title":"Very Lightweight Photo Retouching Network with Conditional Sequential Modulation","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2106.04765","title":"Predicting Deep Neural Network Generalization with Perturbation Response Curves","created":"2021-06-09","cited_by_count":14,"area":null},{"id":"2108.04811","title":"Binary Complex Neural Network Acceleration on FPGA","created":"2021-08-10","cited_by_count":14,"area":null},{"id":"2111.13353","title":"Contrastive Vicinal Space for Unsupervised Domain Adaptation","created":"2021-11-26","cited_by_count":14,"area":null},{"id":"2303.09660","title":"Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detection","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2102.07951","title":"ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks","created":"2021-02-16","cited_by_count":13,"area":null},{"id":"2204.06772","title":"ViTOL: Vision Transformer for Weakly Supervised Object Localization","created":"2022-04-14","cited_by_count":13,"area":null}],"next_cursor":"100"}