Transformers have recently emerged as a powerful tool for learning visual representations.
In this paper, we identify and characterize artifacts in feature maps of both supervised and …

Abstract We propose Cut-and-LEaRn (CutLER), a simple approach for training
unsupervised object detection and segmentation models. We leverage the property of self …

Abstract Vision Transformers (ViTs) and their multi-scale and hierarchical variations have
been successful at capturing image representations but their use has been generally …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

We present Neural Feature Fusion Fields (N3F),\a method that improves dense 2D image
feature extractors when the latter are applied to the analysis of multiple images …

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

We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as
dense visual descriptors. We observe and empirically demonstrate that such features, when …

Humans naturally decompose their environment into entities at the appropriate level of
abstraction to act in the world. Allowing machine learning algorithms to derive this …

Instance segmentation is a fundamental vision task that aims to recognize and segment
each object in an image. However, it requires costly annotations such as bounding boxes …

Progress in self-supervised learning has brought strong general image representation
learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks …