{"list":"other","total":57,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"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":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"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":"1904.09739","title":"Switchable Whitening for Deep Representation Learning","created":"2019-04-22","cited_by_count":106},{"id":"2210.05844","title":"SegViT: Semantic Segmentation with Plain Vision Transformers","created":"2022-10-12","cited_by_count":106},{"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":"2204.03609","title":"Pin the Memory: Learning to Generalize Semantic Segmentation","created":"2022-04-07","cited_by_count":49},{"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":"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":"2209.07695","title":"Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation","created":"2022-09-16","cited_by_count":31},{"id":"2311.17922","title":"A Simple Recipe for Language-guided Domain Generalized Segmentation","created":"2023-11-29","cited_by_count":28},{"id":"2109.14196","title":"WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation","created":"2021-09-29","cited_by_count":25},{"id":"2303.11546","title":"Texture Learning Domain Randomization for Domain Generalized Segmentation","created":"2023-03-21","cited_by_count":24},{"id":"2309.00844","title":"Domain Generalization via Balancing Training Difficulty and Model Capability","created":"2023-09-02","cited_by_count":20},{"id":"2010.05495","title":"Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers","created":"2020-10-12","cited_by_count":17},{"id":"2307.09362","title":"Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement","created":"2023-07-18","cited_by_count":12},{"id":"2309.13258","title":"Order-preserving Consistency Regularization for Domain Adaptation and Generalization","created":"2023-09-23","cited_by_count":11},{"id":"2308.13331","title":"A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation","created":"2023-08-25","cited_by_count":8},{"id":"2305.02578","title":"Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts","created":"2023-05-04","cited_by_count":7}],"next_cursor":null}