The probes are applied on datasets of real images with annotations for the property.

Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the finest pixel granularity.

In the absence of class priors, recent deep clustering methods resort to data augmentation and pseudo-labeling strategies to generate supervision signals.