{"total":391,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964,"area":null},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184,"area":null},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781,"area":"diffusion"},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640,"area":"diffusion"},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636,"area":"diffusion"},{"id":"2112.07804","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","created":"2021-12-15","cited_by_count":516,"area":"diffusion"},{"id":"2110.08985","title":"StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis","created":"2021-10-18","cited_by_count":477,"area":null},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330,"area":null},{"id":"2110.05243","title":"Score-based diffusion models for accelerated MRI","created":"2021-10-08","cited_by_count":311,"area":"diffusion"},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2112.07068","title":"Score-Based Generative Modeling with Critically-Damped Langevin Diffusion","created":"2021-12-14","cited_by_count":233,"area":"diffusion"},{"id":"2112.05637","title":"HeadNeRF: A Real-time NeRF-based Parametric Head Model","created":"2021-12-10","cited_by_count":228,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197,"area":"diffusion"},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185,"area":"wm"},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"area":null},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137,"area":null},{"id":"2104.00670","title":"Unconstrained Scene Generation with Locally Conditioned Radiance Fields","created":"2021-04-01","cited_by_count":130,"area":null},{"id":"2204.08906","title":"Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing","created":"2022-04-19","cited_by_count":126,"area":null},{"id":"2106.04732","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","created":"2021-06-08","cited_by_count":104,"area":null},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104,"area":null},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2409.16211","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","created":"2024-09-24","cited_by_count":98,"area":"diffusion"},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90,"area":null},{"id":"2302.09462","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","created":"2023-02-19","cited_by_count":89,"area":null},{"id":"2103.13425","title":"Diverse Branch Block: Building a Convolution as an Inception-like Unit","created":"2021-03-24","cited_by_count":87,"area":null},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87,"area":null},{"id":"2112.09130","title":"Ensembling Off-the-shelf Models for GAN Training","created":"2021-12-16","cited_by_count":86,"area":null},{"id":"2207.04978","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","created":"2022-07-11","cited_by_count":78,"area":null},{"id":"2112.05130","title":"Multimodal Conditional Image Synthesis with Product-of-Experts GANs","created":"2021-12-09","cited_by_count":75,"area":null},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74,"area":null},{"id":"2104.06954","title":"Aligning Latent and Image Spaces to Connect the Unconnectable","created":"2021-04-14","cited_by_count":70,"area":null},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"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":"2403.14548","title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","created":"2024-03-21","cited_by_count":64,"area":null},{"id":"2111.02447","title":"On the Frequency Bias of Generative Models","created":"2021-11-03","cited_by_count":60,"area":null},{"id":"2306.10619","title":"Towards Stability of Autoregressive Neural Operators","created":"2023-06-18","cited_by_count":59,"area":null},{"id":"2403.12963","title":"FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis","created":"2024-03-19","cited_by_count":59,"area":"diffusion"},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2104.14551","title":"Ensembling with Deep Generative Views","created":"2021-04-29","cited_by_count":53,"area":null},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51,"area":null},{"id":"2501.07730","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","created":"2025-01-13","cited_by_count":50,"area":null},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49,"area":null},{"id":"2112.00639","title":"A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?","created":"2021-12-01","cited_by_count":48,"area":null},{"id":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48,"area":null},{"id":"2108.05137","title":"Zero-Shot Day-Night Domain Adaptation with a Physics Prior","created":"2021-08-11","cited_by_count":47,"area":null},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44,"area":null},{"id":"2111.15242","title":"ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation","created":"2021-11-30","cited_by_count":41,"area":null},{"id":"2201.04873","title":"VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting","created":"2022-01-13","cited_by_count":37,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2109.05721","title":"ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment","created":"2021-09-13","cited_by_count":34,"area":null},{"id":"2202.14020","title":"State-of-the-Art in the Architecture, Methods and Applications of StyleGAN","created":"2022-02-28","cited_by_count":34,"area":null},{"id":"2403.05369","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","created":"2024-03-08","cited_by_count":34,"area":null},{"id":"2104.09789","title":"Does enhanced shape bias improve neural network robustness to common corruptions?","created":"2021-04-20","cited_by_count":32,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2404.12388","title":"VideoGigaGAN: Towards Detail-rich Video Super-Resolution","created":"2024-04-18","cited_by_count":30,"area":null},{"id":"2107.13335","title":"WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification","created":"2021-07-28","cited_by_count":29,"area":null},{"id":"2203.10821","title":"Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields","created":"2022-03-21","cited_by_count":29,"area":null},{"id":"2204.02844","title":"Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training","created":"2022-04-06","cited_by_count":29,"area":null},{"id":"2204.00491","title":"FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting","created":"2022-04-01","cited_by_count":28,"area":null},{"id":"2106.05121","title":"Grounding inductive biases in natural images:invariance stems from variations in data","created":"2021-06-09","cited_by_count":27,"area":null},{"id":"2203.04412","title":"ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"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":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2108.03489","title":"Impact of Aliasing on Generalization in Deep Convolutional Networks","created":"2021-08-07","cited_by_count":25,"area":null},{"id":"2304.09941","title":"A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypoints","created":"2023-04-19","cited_by_count":25,"area":null},{"id":"2102.06315","title":"Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization","created":"2021-02-11","cited_by_count":24,"area":null},{"id":"2106.02297","title":"Fre-GAN: Adversarial Frequency-consistent Audio Synthesis","created":"2021-06-04","cited_by_count":24,"area":null},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2111.08251","title":"Enabling equivariance for arbitrary Lie groups","created":"2021-11-16","cited_by_count":22,"area":null},{"id":"2203.01386","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","created":"2022-03-02","cited_by_count":21,"area":null},{"id":"2204.08179","title":"Real-World Deep Local Motion Deblurring","created":"2022-04-18","cited_by_count":21,"area":null},{"id":"2205.07362","title":"What is an equivariant neural network?","created":"2022-05-15","cited_by_count":21,"area":null},{"id":"2305.01604","title":"The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold","created":"2023-05-02","cited_by_count":21,"area":null},{"id":"2305.06024","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2110.05861","title":"Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2307.10235","title":"Towards Viewpoint-Invariant Visual Recognition via Adversarial Training","created":"2023-07-16","cited_by_count":19,"area":null},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2101.10808","title":"Fast Facial Landmark Detection and Applications: A Survey","created":"2021-01-12","cited_by_count":18,"area":null},{"id":"2105.03072","title":"NTIRE 2021 Challenge on Perceptual Image Quality Assessment","created":"2021-05-07","cited_by_count":18,"area":null},{"id":"2108.13576","title":"Dead Pixel Test Using Effective Receptive Field","created":"2021-08-31","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":"2108.01285","title":"Toward Spatially Unbiased Generative Models","created":"2021-08-03","cited_by_count":17,"area":null},{"id":"2212.07378","title":"3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping","created":"2022-12-14","cited_by_count":17,"area":null},{"id":"2303.01748","title":"A Complete Recipe for Diffusion Generative Models","created":"2023-03-03","cited_by_count":17,"area":"diffusion"},{"id":"2304.12944","title":"Latent Traversals in Generative Models as Potential Flows","created":"2023-04-25","cited_by_count":17,"area":null},{"id":"2402.18933","title":"Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration","created":"2024-02-29","cited_by_count":17,"area":null},{"id":"2103.02695","title":"Shift Invariance Can Reduce Adversarial Robustness","created":"2021-03-03","cited_by_count":16,"area":null},{"id":"2110.15156","title":"Blending Anti-Aliasing into Vision Transformer","created":"2021-10-28","cited_by_count":16,"area":null},{"id":"2207.02796","title":"Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution","created":"2022-07-06","cited_by_count":16,"area":null}],"next_cursor":"100"}