Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentation

arXiv:2603.25131 · cs.CV · Submitted 2026-03-26 · Read on arXiv

cs.CV

Submitted: 2026-03-26

Updated: 2026-03-26

Comments: Accepted to CVPR26

Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 32226-32235

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Pseudo-labels — 2× in this paper · explained in 2 episodes
• Semantic Segmentation — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Domain Shift — 1× in this paper · explained in 6 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• While Unsupervised Domain Adaptation — 1× in this paper

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