2 papers
cs.CV2026
Closing the Confusion Loop: CLIP-Guided Alignment for Source-Free Domain Adaptation
Shanshan Wang, Ziying Feng, Xiaozheng Shen +4
Source-Free Domain Adaptation (SFDA) tackles the problem of adapting a pre-trained source model to an unlabeled target domain without accessing any source data, which is quite suit…
cs.CV2025
Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance
Zhenwei He, Hongsu Ni
Single-domain generalization for object detection (S-DGOD) seeks to transfer learned representations from a single source domain to unseen target domains. While recent approaches h…