Unsupervised localization and segmentation are long-standing computer vision challenges
that involve decomposing an image into semantically-meaningful segments without any …

Localizing objects in image collections without supervision can help to avoid expensive
annotation campaigns. We propose a simple approach to this problem, that leverages the …

In this paper, we describe a graph-based algorithm that uses the features obtained by a self-
supervised transformer to detect and segment salient objects in images and videos. With this …

Recent advances in self-supervised visual representation learning have paved the way for
unsupervised methods tackling tasks such as object discovery and instance segmentation …

In this paper, we show that recent advances in self-supervised feature learning enable
unsupervised object discovery and semantic segmentation with a performance that matches …

We introduce MOVE, a novel method to segment objects without any form of supervision.
MOVE exploits the fact that foreground objects can be shifted locally relative to their initial …

Transformers trained with self-supervision using self-distillation loss (DINO) have been
shown to produce attention maps that highlight salient foreground objects. In this paper, we …

Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of
objects from the background within a scene without relying on labeled datasets, which …

The recent enthusiasm for open-world vision systems show the high interest of the
community to perform perception tasks outside of the closed-vocabulary benchmark setups …

The aim of weakly supervised object co-localization is to locate different objects of the same
superclass in a dataset. Recent methods achieve impressive co-localization performance by …