CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
cs.CV, cs.LG
Submitted: 2025-04-19
Updated: 2026-09-21
Comments: Published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
DOI: 10.1109/TPAMI.2026.3651700
Code: https://github.com/jindongli-Ai/Survey
Project page: https://beerys.github.io/CaltechCameraTraps
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
- DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
- Exploring Visual Prompts for Adapting Large-Scale Models
- Soft Prompt Generation for Domain Generalization
- PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
- Vision Transformer Adapter for Dense Predictions
- Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
- Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
- Making Pre-trained Language Models Better Few-shot Learners
- A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Unsupervised Prompt Learning for Vision-Language Models
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- GalLoP: Learning Global and Local Prompts for Vision-Language Models
- The Power of Scale for Parameter-Efficient Prompt Tuning
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
- Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation
- Training-Free Unsupervised Prompt for Vision-Language Models
- Decoupled Weight Decay Regularization
- Fine-Grained Visual Classification of Aircraft
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models