unsupervised domain adaptation
A technique that allows models trained in one domain to adapt to a different but related domain without requiring labeled data, aiming to improve model performance in varied environments or contexts.
- BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation
- Breakthrough Sensor-Limited Single View: Towards Implicit Temporal Dynamics for Time Series Domain Adaptation
- Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation
- Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation
- GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset
- Learning to Zoom with Anatomical Relations for Medical Structure Detection
- SGCD: Stain-Guided CycleDiffusion for Unsupervised Domain Adaptation of Histopathology Image Classification
- Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
- Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation