Out-of-Distribution Semantic Segmentation with Disentangled and Calibrated Representation

• Published in: IEEE transactions on circuits and systems for video technology p. 1
• Main Authors: Wan, Maoxian, Li, Kaige, Geng, Qichuan, Su, Binyi, Zhou, Zhong
• Format: Journal Article
• Language: English
• Published: IEEE 2025
• Subjects: Accuracy; Data models; disentangled representations; Image reconstruction; out-of-distribution; Overfitting; Semantic segmentation; Shape; Synthetic data; Training; Training data; Uncertainty

Out-of-distribution (OoD) semantic segmentation aims to recognize pixels of classes undefined in the training dataset. Existing methods mostly focus on training the model to fit real OoD data samples to identify OoD pixels, which requires extra data collection and annotation efforts. By contrast, sy...