Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning

灵敏度感知视觉参数高效微调

On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

关于开放世界测试时训练的鲁棒性：动态原型扩展的自我训练

Boosting Novel Category Discovery over Domains with Soft Contrastive Learning and all in One Classifier

通过软对比学习和多合一分类器促进领域的新类别发现

A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning

持续半监督学习的软最近邻框架

GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation

GraphEcho：用于超声心动图视频分割的图驱动无监督域适应

ViperGPT: Visual Inference via Python Execution for Reasoning

ViperGPT：通过 Python 执行进行视觉推理以进行推理

Improved Visual Fine-Tuning with Natural Language Supervision

通过自然语言监督改进视觉微调