{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"1807.09441","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","created":"2018-07-25","cited_by_count":364},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2204.02548","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","created":"2022-04-06","cited_by_count":89},{"id":"2301.05499","title":"CLIP the Gap: A Single Domain Generalization Approach for Object Detection","created":"2023-01-13","cited_by_count":87},{"id":"2312.04265","title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-07","cited_by_count":83},{"id":"2204.00822","title":"Semantic-Aware Domain Generalized Segmentation","created":"2022-04-02","cited_by_count":79},{"id":"2204.01446","title":"WildNet: Learning Domain Generalized Semantic Segmentation from the Wild","created":"2022-04-04","cited_by_count":76},{"id":"2207.04892","title":"Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation","created":"2022-07-11","cited_by_count":70},{"id":"2108.02376","title":"Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation","created":"2021-08-05","cited_by_count":57},{"id":"1905.13277","title":"Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence","created":"2019-05-30","cited_by_count":54},{"id":"2204.03609","title":"Pin the Memory: Learning to Generalize Semantic Segmentation","created":"2022-04-07","cited_by_count":49},{"id":"2312.03048","title":"DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control","created":"2023-12-05","cited_by_count":45},{"id":"2312.12176","title":"All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes","created":"2023-12-19","cited_by_count":41},{"id":"2212.00979","title":"PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization","created":"2022-12-02","cited_by_count":39},{"id":"2312.09788","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-15","cited_by_count":34},{"id":"2102.02811","title":"CrossNorm and SelfNorm for Generalization under Distribution Shifts","created":"2021-02-04","cited_by_count":33},{"id":"2305.13031","title":"HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation","created":"2023-05-22","cited_by_count":32},{"id":"2204.01587","title":"FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation","created":"2022-04-04","cited_by_count":31},{"id":"2307.00371","title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","created":"2023-07-01","cited_by_count":30},{"id":"2405.14497","title":"Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment","created":"2024-05-23","cited_by_count":29},{"id":"2405.15225","title":"Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection","created":"2024-05-24","cited_by_count":29},{"id":"2311.17922","title":"A Simple Recipe for Language-guided Domain Generalized Segmentation","created":"2023-11-29","cited_by_count":28},{"id":"2312.01850","title":"Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation","created":"2023-12-04","cited_by_count":28},{"id":"2303.11546","title":"Texture Learning Domain Randomization for Domain Generalized Segmentation","created":"2023-03-21","cited_by_count":24},{"id":"2402.18447","title":"Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization","created":"2024-02-28","cited_by_count":24},{"id":"2407.18568","title":"Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation","created":"2024-07-26","cited_by_count":22},{"id":"2312.12133","title":"Object-Aware Domain Generalization for Object Detection","created":"2023-12-19","cited_by_count":21},{"id":"2407.09033","title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","created":"2024-07-12","cited_by_count":21},{"id":"2309.00844","title":"Domain Generalization via Balancing Training Difficulty and Model Capability","created":"2023-09-02","cited_by_count":20},{"id":"2304.02222","title":"DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation","created":"2023-04-05","cited_by_count":19},{"id":"2403.06122","title":"Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning","created":"2024-03-10","cited_by_count":18},{"id":"2010.05495","title":"Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers","created":"2020-10-12","cited_by_count":17},{"id":"2407.15085","title":"Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization","created":"2024-07-21","cited_by_count":14},{"id":"2410.22461","title":"Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection","created":"2024-10-29","cited_by_count":13},{"id":"2307.09362","title":"Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement","created":"2023-07-18","cited_by_count":12},{"id":"2303.01906","title":"Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning","created":"2023-03-03","cited_by_count":11},{"id":"2309.13258","title":"Order-preserving Consistency Regularization for Domain Adaptation and Generalization","created":"2023-09-23","cited_by_count":11},{"id":"2311.18331","title":"MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation","created":"2023-11-30","cited_by_count":11},{"id":"2404.10966","title":"Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation","created":"2024-04-17","cited_by_count":8},{"id":"2408.13838","title":"Exploring Reliable Matching with Phase Enhancement for Night-time Semantic Segmentation","created":"2024-08-25","cited_by_count":1}],"next_cursor":null}