{"total":142,"rows":[{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184,"area":null},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471,"area":null},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152,"area":null},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122,"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":"2307.15421","title":"MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression","created":"2023-07-28","cited_by_count":58,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"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":"2305.17592","title":"Approximation-Generalization Trade-offs under (Approximate) Group Equivariance","created":"2023-05-27","cited_by_count":46,"area":null},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2203.14333","title":"Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning","created":"2022-03-27","cited_by_count":26,"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":"2203.11105","title":"High-fidelity GAN Inversion with Padding Space","created":"2022-03-21","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":"2405.11905","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","created":"2024-05-20","cited_by_count":23,"area":null},{"id":"2207.08877","title":"Prior Knowledge Guided Unsupervised Domain Adaptation","created":"2022-07-18","cited_by_count":20,"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":"2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","created":"2021-12-02","cited_by_count":19,"area":null},{"id":"2304.14329","title":"Learning to Extrapolate: A Transductive Approach","created":"2023-04-27","cited_by_count":19,"area":null},{"id":"2311.15607","title":"Spatially Covariant Image Registration with Text Prompts","created":"2023-11-27","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":"2112.03212","title":"Physically Consistent Neural Networks for building thermal modeling: theory and analysis","created":"2021-12-06","cited_by_count":17,"area":null},{"id":"2204.02163","title":"Leveraging Equivariant Features for Absolute Pose Regression","created":"2022-04-05","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":"2106.02523","title":"Hallucination In Object Detection -- A Study In Visual Part Verification","created":"2021-06-04","cited_by_count":16,"area":null},{"id":"2107.09539","title":"Parametric Scattering Networks","created":"2021-07-20","cited_by_count":16,"area":null},{"id":"2111.11398","title":"Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks","created":"2021-11-22","cited_by_count":15,"area":null},{"id":"2210.13604","title":"The Robustness Limits of SoTA Vision Models to Natural Variation","created":"2022-10-24","cited_by_count":15,"area":null},{"id":"2302.01409","title":"Hyperbolic Contrastive Learning","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2304.02628","title":"What Affects Learned Equivariance in Deep Image Recognition Models?","created":"2023-04-05","cited_by_count":15,"area":null},{"id":"2106.11160","title":"Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics","created":"2021-06-21","cited_by_count":14,"area":null},{"id":"2207.12258","title":"Equivariance and Invariance Inductive Bias for Learning from Insufficient Data","created":"2022-07-25","cited_by_count":14,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2503.09419","title":"Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space","created":"2025-03-12","cited_by_count":14,"area":"diffusion"},{"id":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2205.13900","title":"How Tempering Fixes Data Augmentation in Bayesian Neural Networks","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2105.02468","title":"Relative stability toward diffeomorphisms indicates performance in deep nets","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2108.07884","title":"Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs","created":"2021-08-17","cited_by_count":12,"area":null},{"id":"2108.13122","title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","created":"2021-08-30","cited_by_count":12,"area":null},{"id":"2203.07302","title":"Mixed Evidence for Gestalt Grouping in Deep Neural Networks","created":"2022-03-14","cited_by_count":12,"area":null},{"id":"2204.08563","title":"Cylin-Painting: Seamless {360\\textdegree} Panoramic Image Outpainting and Beyond","created":"2022-04-18","cited_by_count":12,"area":null},{"id":"2403.18360","title":"Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation","created":"2024-03-27","cited_by_count":12,"area":null},{"id":"2101.10143","title":"Spectral Leakage and Rethinking the Kernel Size in CNNs","created":"2021-01-25","cited_by_count":11,"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":"2110.00899","title":"Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function","created":"2021-10-03","cited_by_count":11,"area":null},{"id":"2201.12133","title":"O-ViT: Orthogonal Vision Transformer","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2301.07895","title":"Spatially Covariant Lesion Segmentation","created":"2023-01-19","cited_by_count":10,"area":null},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2206.10421","title":"Rethinking Audio-visual Synchronization for Active Speaker Detection","created":"2022-06-21","cited_by_count":9,"area":null},{"id":"2109.09363","title":"Performance and accuracy assessments of an incompressible fluid solver coupled with a deep Convolutional Neural Network","created":"2021-09-20","cited_by_count":8,"area":null},{"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":"2301.01661","title":"RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning","created":"2023-01-04","cited_by_count":8,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2101.05846","title":"How Shift Equivariance Impacts Metric Learning for Instance Segmentation","created":"2021-01-14","cited_by_count":7,"area":null},{"id":"2103.10097","title":"Stride and Translation Invariance in CNNs","created":"2021-03-18","cited_by_count":7,"area":null},{"id":"2112.09195","title":"Mitigating the Bias of Centered Objects in Common Datasets","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2203.10489","title":"TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing","created":"2022-03-20","cited_by_count":7,"area":null},{"id":"2208.04654","title":"Extending GCC-PHAT using Shift Equivariant Neural Networks","created":"2022-08-09","cited_by_count":7,"area":null},{"id":"2310.13215","title":"Zone Evaluation: Revealing Spatial Bias in Object Detection","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2310.19368","title":"Color Equivariant Convolutional Networks","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2404.10727","title":"How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2105.05838","title":"Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning","created":"2021-05-12","cited_by_count":6,"area":null},{"id":"2211.09286","title":"Permutation-Invariant Tabular Data Synthesis","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2302.01740","title":"SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2103.04020","title":"NeRD: Neural Representation of Distribution for Medical Image Segmentation","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2103.15812","title":"LatentKeypointGAN: Controlling Images via Latent Keypoints","created":"2021-03-29","cited_by_count":5,"area":null},{"id":"2106.04914","title":"Exploiting Learned Symmetries in Group Equivariant Convolutions","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2303.08434","title":"DeDA: Deep Directed Accumulator","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2410.11774","title":"Fractal Calibration for long-tailed object detection","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2104.11691","title":"Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities","created":"2021-04-22","cited_by_count":4,"area":null},{"id":"2108.11900","title":"Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning","created":"2021-08-26","cited_by_count":4,"area":null},{"id":"2205.02887","title":"Evaluating Context for Deep Object Detectors","created":"2022-05-05","cited_by_count":4,"area":null},{"id":"2209.13233","title":"Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification","created":"2022-09-27","cited_by_count":4,"area":null},{"id":"2211.07157","title":"ParCNetV2: Oversized Kernel with Enhanced Attention","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2212.12478","title":"Image Classification with Small Datasets: Overview and Benchmark","created":"2022-12-23","cited_by_count":4,"area":null},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2307.16203","title":"Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning","created":"2023-07-30","cited_by_count":4,"area":null},{"id":"2308.11316","title":"Using and Abusing Equivariance","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2312.02136","title":"BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2402.00240","title":"Spectral Norm of Convolutional Layers with Circular and Zero Paddings","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2104.05997","title":"Tracking translation invariance in CNNs","created":"2021-04-13","cited_by_count":3,"area":null},{"id":"2201.13065","title":"Rigidity Preserving Image Transformations and Equivariance in Perspective","created":"2022-01-31","cited_by_count":3,"area":null},{"id":"2204.08601","title":"A Tour of Visualization Techniques for Computer Vision Datasets","created":"2022-04-19","cited_by_count":3,"area":null},{"id":"2206.01202","title":"Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2207.02349","title":"Generalization to translation shifts: a study in architectures and augmentations","created":"2022-07-05","cited_by_count":3,"area":null},{"id":"2207.10582","title":"Designing An Illumination-Aware Network for Deep Image Relighting","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2306.08191","title":"Solving Large-scale Spatial Problems with Convolutional Neural Networks","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2407.02934","title":"PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2503.18294","title":"LGPS: A Lightweight GAN-Based Approach for Polyp Segmentation in Colonoscopy Images","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2508.10637","title":"Processing and acquisition traces in visual encoders: What does CLIP know about your camera?","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2509.21265","title":"MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2106.15331","title":"Improved Padding in CNNs for Quantitative Susceptibility Mapping","created":"2021-06-21","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}],"next_cursor":"100"}