Self-training methods have gained significant attention in recent years due to their
effectiveness in leveraging small labeled datasets and large unlabeled observations for …

Masked image modeling (MIM) has attracted much research attention due to its promising
potential for learning scalable visual representations. In typical approaches, models usually …

Deep learning models are often evaluated in scenarios where the data distribution is
different from those used in the training and validation phases. The discrepancy presents a …

Semantic segmentation usually suffers from a long tail data distribution. Due to the
imbalanced number of samples across categories, the features of those tail classes may get …

We study unsupervised domain adaptation (UDA) for semantic segmentation. Currently, a
popular UDA framework lies in self-training which endows the model with two-fold …

Deep neural networks (DNNs) have proven their capabilities in the past years and play a
significant role in environment perception for the challenging application of automated …

The crux of label-efficient semantic segmentation is to produce high-quality pseudo-labels to
leverage a large amount of unlabeled or weakly labeled data. A common practice is to select …

Abstract Domain-adaptive semantic segmentation aims to transfer knowledge from a labeled
source domain to an unlabeled target domain. However, existing methods primarily focus on …

This paper presents a simple but performant semi-supervised semantic segmentation
approach called CorrMatch. Previous approaches mostly employ complicated training …

Unsupervised object-centric learning aims to decompose scenes into interpretable object
entities termed slots. Slot-based auto-encoders stand out as a prominent method for this …