{"list":"other","total":64,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"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":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186},{"id":"1712.00479","title":"Image to Image Translation for Domain Adaptation","created":"2017-12-01","cited_by_count":171},{"id":"2103.02370","title":"FSDR: Frequency Space Domain Randomization for Domain Generalization","created":"2021-03-03","cited_by_count":164},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146},{"id":"2202.03958","title":"Uncertainty Modeling for Out-of-Distribution Generalization","created":"2022-02-08","cited_by_count":125},{"id":"1810.02575","title":"Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime","created":"2018-10-05","cited_by_count":122},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"id":"1808.01265","title":"Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding","created":"2018-08-03","cited_by_count":98},{"id":"2410.16261","title":"Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance","created":"2024-10-21","cited_by_count":94},{"id":"2303.17393","title":"Dynamic Conceptional Contrastive Learning for Generalized Category Discovery","created":"2023-03-30","cited_by_count":92},{"id":"2204.02548","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","created":"2022-04-06","cited_by_count":89},{"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":"2212.03241","title":"P{\\O}DA: Prompt-driven Zero-shot Domain Adaptation","created":"2022-12-06","cited_by_count":60},{"id":"2305.16742","title":"Parameter-Efficient Fine-Tuning without Introducing New Latency","created":"2023-05-26","cited_by_count":59},{"id":"2108.02376","title":"Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation","created":"2021-08-05","cited_by_count":57},{"id":"2212.03220","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","created":"2022-12-06","cited_by_count":57},{"id":"2311.16510","title":"Source-Free Domain Adaptation with Frozen Multimodal Foundation Model","created":"2023-11-27","cited_by_count":55},{"id":"1905.12213","title":"Where is the Information in a Deep Neural Network?","created":"2019-05-29","cited_by_count":42},{"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":"1910.11645","title":"Reducing Domain Gap by Reducing Style Bias","created":"2019-10-25","cited_by_count":35},{"id":"2312.03502","title":"Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation","created":"2023-12-06","cited_by_count":31},{"id":"2303.09792","title":"Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction","created":"2023-03-17","cited_by_count":28},{"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":"2008.02520","title":"Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification","created":"2020-08-06","cited_by_count":23},{"id":"2407.18568","title":"Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation","created":"2024-07-26","cited_by_count":22},{"id":"2407.09033","title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","created":"2024-07-12","cited_by_count":21},{"id":"2312.02021","title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","created":"2023-12-04","cited_by_count":20},{"id":"2412.15541","title":"ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model","created":"2024-12-20","cited_by_count":10},{"id":"2406.06813","title":"Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation","created":"2024-06-10","cited_by_count":8},{"id":"1901.05946","title":"Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation","created":"2019-01-17","cited_by_count":4},{"id":"2410.21708","title":"Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation","created":"2024-10-29","cited_by_count":4},{"id":"2312.06331","title":"Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation","created":"2023-12-11","cited_by_count":3}],"next_cursor":null}