{"list":"other","total":79,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2103.10504","title":"UNETR: Transformers for 3D Medical Image Segmentation","created":"2021-03-18","cited_by_count":959},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2201.01266","title":"Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images","created":"2022-01-04","cited_by_count":830},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"1902.03368","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2019-02-09","cited_by_count":669},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"1708.08987","title":"Deep Learning for Medical Image Analysis","created":"2017-08-17","cited_by_count":401},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2004.08790","title":"UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation","created":"2020-04-19","cited_by_count":332},{"id":"1810.11654","title":"3D MRI brain tumor segmentation using autoencoder regularization","created":"2018-10-27","cited_by_count":328},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"1808.08114","title":"Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images","created":"2018-08-22","cited_by_count":272},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1603.05959","title":"Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation","created":"2016-03-18","cited_by_count":263},{"id":"1903.02740","title":"CE-Net: Context Encoder Network for 2D Medical Image Segmentation","created":"2019-03-07","cited_by_count":220},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"2212.11972","title":"Scalable Adaptive Computation for Iterative Generation","created":"2022-12-22","cited_by_count":195},{"id":"2203.04967","title":"UNeXt: MLP-based Rapid Medical Image Segmentation Network","created":"2022-03-09","cited_by_count":185},{"id":"1906.04928","title":"Deep Learning for Spatio-Temporal Data Mining: A Survey","created":"2019-06-11","cited_by_count":172},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"id":"2009.13120","title":"Medical Image Segmentation Using Deep Learning: A Survey","created":"2020-09-28","cited_by_count":164},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2206.09959","title":"Global Context Vision Transformers","created":"2022-06-20","cited_by_count":98},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80},{"id":"2203.06398","title":"SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection","created":"2022-03-12","cited_by_count":74},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51},{"id":"2012.05440","title":"Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding","created":"2020-12-10","cited_by_count":48},{"id":"2104.05623","title":"Rethinking and Improving the Robustness of Image Style Transfer","created":"2021-04-08","cited_by_count":48},{"id":"1806.01313","title":"Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images","created":"2018-06-04","cited_by_count":42},{"id":"2106.06908","title":"Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation","created":"2021-06-13","cited_by_count":33},{"id":"2006.12030","title":"DO-Conv: Depthwise Over-parameterized Convolutional Layer","created":"2020-06-22","cited_by_count":28},{"id":"2207.05409","title":"Knowledge Condensation Distillation","created":"2022-07-12","cited_by_count":20},{"id":"2306.07598","title":"Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images","created":"2023-06-13","cited_by_count":18},{"id":"2103.09097","title":"Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification","created":"2021-03-16","cited_by_count":15},{"id":"2105.14732","title":"Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation","created":"2021-05-31","cited_by_count":15},{"id":"2009.05722","title":"Generator Versus Segmentor: Pseudo-healthy Synthesis","created":"2020-09-12","cited_by_count":12},{"id":"2204.07963","title":"AFSC: Adaptive Fourier Space Compression for Anomaly Detection","created":"2022-04-17","cited_by_count":12},{"id":"2103.09094","title":"Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation","created":"2021-03-16","cited_by_count":11},{"id":"2404.02446","title":"Masked Completion via Structured Diffusion with White-Box Transformers","created":"2024-04-03","cited_by_count":9},{"id":"2404.19265","title":"Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translation","created":"2024-04-30","cited_by_count":7},{"id":"2405.03545","title":"Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors","created":"2024-05-06","cited_by_count":5},{"id":"2405.16850","title":"UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation","created":"2024-05-27","cited_by_count":3},{"id":"2403.15943","title":"Advanced Feature Manipulation for Enhanced Change Detection Leveraging Natural Language Models","created":"2024-03-23","cited_by_count":1},{"id":"2405.08226","title":"Self-Normalizing Foundation Model for Enhanced Multi-Omics Data Analysis in Oncology","created":"2024-05-13","cited_by_count":1}],"next_cursor":null}