{"total":119,"rows":[{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135,"area":null},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2208.02814","title":"Conformal Risk Control","created":"2022-08-04","cited_by_count":299,"area":null},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288,"area":null},{"id":"2110.01052","title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","created":"2021-10-03","cited_by_count":271,"area":null},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"area":null},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2210.02438","title":"DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics","created":"2022-10-05","cited_by_count":106,"area":"diffusion"},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87,"area":null},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79,"area":null},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35,"area":null},{"id":"2108.00146","title":"T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning","created":"2021-07-31","cited_by_count":26,"area":null},{"id":"2110.10955","title":"Multi-label Classification with Partial Annotations using Class-aware Selective Loss","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24,"area":null},{"id":"2108.10566","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","created":"2021-08-24","cited_by_count":23,"area":null},{"id":"2102.05610","title":"Searching for Fast Model Families on Datacenter Accelerators","created":"2021-02-10","cited_by_count":22,"area":null},{"id":"2310.16112","title":"Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge","created":"2023-10-24","cited_by_count":22,"area":null},{"id":"2106.06195","title":"MlTr: Multi-label Classification with Transformer","created":"2021-06-11","cited_by_count":21,"area":null},{"id":"2102.11646","title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","created":"2021-02-23","cited_by_count":20,"area":null},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2304.07230","title":"PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition","created":"2023-04-14","cited_by_count":19,"area":null},{"id":"2103.10895","title":"Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark","created":"2021-03-19","cited_by_count":17,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2212.13629","title":"Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions","created":"2022-12-27","cited_by_count":14,"area":null},{"id":"2205.09904","title":"Deep transfer learning for image classification: a survey","created":"2022-05-20","cited_by_count":13,"area":null},{"id":"2103.03768","title":"VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2021-03-05","cited_by_count":11,"area":null},{"id":"2203.04187","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","created":"2022-03-08","cited_by_count":11,"area":null},{"id":"2310.10443","title":"Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2504.16940","title":"Better artificial intelligence does not mean better models of biology","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2305.16347","title":"Prompt Evolution for Generative AI: A Classifier-Guided Approach","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2406.14830","title":"CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation","created":"2024-06-21","cited_by_count":9,"area":null},{"id":"2201.06945","title":"It's All in the Head: Representation Knowledge Distillation through Classifier Sharing","created":"2022-01-18","cited_by_count":8,"area":"distill"},{"id":"2201.08625","title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2202.08978","title":"Cyclical Focal Loss","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2204.03475","title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2211.05232","title":"MuMIC -- Multimodal Embedding for Multi-label Image Classification with Tempered Sigmoid","created":"2022-11-02","cited_by_count":8,"area":null},{"id":"2307.03967","title":"End-to-End Supervised Multilabel Contrastive Learning","created":"2023-07-08","cited_by_count":8,"area":null},{"id":"2404.06287","title":"Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training","created":"2024-04-09","cited_by_count":8,"area":null},{"id":"2103.08640","title":"UPANets: Learning from the Universal Pixel Attention Networks","created":"2021-03-15","cited_by_count":7,"area":null},{"id":"2205.00841","title":"GPUNet: Searching the Deployable Convolution Neural Networks for GPUs","created":"2022-04-26","cited_by_count":7,"area":null},{"id":"2302.13334","title":"Knowledge Restore and Transfer for Multi-label Class-Incremental Learning","created":"2023-02-26","cited_by_count":7,"area":null},{"id":"2306.16016","title":"Positive Label Is All You Need for Multi-Label Classification","created":"2023-06-28","cited_by_count":7,"area":null},{"id":"2112.03814","title":"A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images","created":"2021-12-07","cited_by_count":6,"area":null},{"id":"2202.05535","title":"A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2206.14098","title":"RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network","created":"2022-06-28","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":"2403.12559","title":"Confidence Self-Calibration for Multi-Label Class-Incremental Learning","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2511.21519","title":"Self-Paced Learning for Images of Antinuclear Antibodies","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2202.08835","title":"General Cyclical Training of Neural Networks","created":"2022-02-17","cited_by_count":5,"area":null},{"id":"2207.02410","title":"A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation","created":"2022-07-06","cited_by_count":5,"area":null},{"id":"2210.13782","title":"Towards Trustworthy Multi-label Sewer Defect Classification via Evidential Deep Learning","created":"2022-10-25","cited_by_count":5,"area":null},{"id":"2301.04494","title":"Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains","created":"2023-01-11","cited_by_count":5,"area":null},{"id":"2302.08572","title":"Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers","created":"2023-02-16","cited_by_count":5,"area":null},{"id":"2410.05500","title":"Residual Kolmogorov-Arnold Network for Enhanced Deep Learning","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2205.00001","title":"Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2209.06585","title":"Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2210.11158","title":"VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2304.05361","title":"Asymmetric Polynomial Loss For Multi-Label Classification","created":"2023-04-10","cited_by_count":4,"area":null},{"id":"2503.17017","title":"Specifying What You Know or Not for Multi-Label Class-Incremental Learning","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2301.10611","title":"Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2312.02985","title":"FocalPose++: Focal Length and Object Pose Estimation via Render and Compare","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2401.01448","title":"ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification","created":"2024-01-02","cited_by_count":3,"area":null},{"id":"2107.08585","title":"Non-binary deep transfer learning for image classification","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2110.01521","title":"Balanced Masked and Standard Face Recognition","created":"2021-10-04","cited_by_count":2,"area":null},{"id":"2110.08842","title":"Exploring Novel Pooling Strategies for Edge Preserved Feature Maps in Convolutional Neural Networks","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2204.04420","title":"Investigating Deep Learning Benchmarks for Electrocardiography Signal Processing","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2301.10750","title":"Out of Distribution Performance of State of Art Vision Model","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2302.10266","title":"Kernel function impact on convolutional neural networks","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2306.10079","title":"M3PT: A Multi-Modal Model for POI Tagging","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2308.07223","title":"Distance Matters For Improving Performance Estimation Under Covariate Shift","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2406.15104","title":"Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors","created":"2024-06-21","cited_by_count":2,"area":null},{"id":"2408.12161","title":"Rebalancing Multi-Label Class-Incremental Learning","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2507.01667","title":"What does really matter in image goal navigation?","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2105.04309","title":"Multi-modal Conditional Bounding Box Regression for Music Score Following","created":"2021-05-10","cited_by_count":1,"area":null},{"id":"2108.02032","title":"Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators","created":"2021-08-04","cited_by_count":1,"area":null},{"id":"2110.14461","title":"Hand gesture detection in tests performed by older adults","created":"2021-10-27","cited_by_count":1,"area":null},{"id":"2212.07936","title":"A Study on the Intersection of GPU Utilization and CNN Inference","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2302.13571","title":"FLAG: Fast Label-Adaptive Aggregation for Multi-label Classification in Federated Learning","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2310.16483","title":"Gramian Attention Heads are Strong yet Efficient Vision Learners","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2401.14336","title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2403.07603","title":"ProPML: Probability Partial Multi-label Learning","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2403.19605","title":"Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2407.20062","title":"SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation","created":"2024-07-29","cited_by_count":1,"area":"distill"},{"id":"2512.23486","title":"Multi-label Classification with Panoptic Context Aggregation Networks","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2109.12499","title":"PETA: Photo Albums Event Recognition using Transformers Attention","created":"2021-09-26","cited_by_count":0,"area":null},{"id":"2111.14059","title":"NoFADE: Analyzing Diminishing Returns on CO2 Investment","created":"2021-11-28","cited_by_count":0,"area":null},{"id":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2207.05137","title":"Towards Effective Multi-Label Recognition Attacks via Knowledge Graph Consistency","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2210.13716","title":"ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition","created":"2022-10-25","cited_by_count":0,"area":null},{"id":"2210.14147","title":"Food Ingredients Recognition through Multi-label Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2310.14453","title":"Skipped Feature Pyramid Network with Grid Anchor for Object Detection","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2405.15860","title":"Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification","created":"2024-05-24","cited_by_count":0,"area":null}],"next_cursor":"100"}