Skip to content
Open access

MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation

Sep 2026 · International Journal of Computer Vision · Vol 134 · 0 citations · 88 references
Computer Science

Abstract

Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g., synthetic) and an unlabeled target domain to bridge the distribution gap. Existing panoptic UDA methods rely on teacher-student consistency learning built upon suboptimal per-pixel segmentation architectures. In contrast, state-of-the-art mask transformers are rarely adopted due to their pronounced vulnerability to confirmation bias in consistency learning, where erroneous teacher predictions are reinforced during training. Our earlier approach, MC-PanDA (Martinović et al., 2024), mitigates this issue through fine-grained confidence estimation, which suppresses gradients from unreliable masks while sampling informative yet reliable locations for loss computation. However, this method entails a complex multi-stage training and requires careful hyperparameter tuning. This work presents MC-PanDA++, which addresses these limitations by introducing: (i) self-supervised vision encoders that provide a stronger and more robust initialization, further reducing the reliance on human annotations, (ii) per-class, self-adapting mask-wide loss scaling that stabilizes training and enables the use of a single set of hyperparameters across domains, and (iii) a single-stage training pipeline that significantly decreases overall conceptual complexity. Together, these improvements result in a conceptually simpler, better-performing, and more robust method for domain-adaptive panoptics. We will release the source code and checkpoints.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.