Unsupervised Object Localization
5 papers with code • 3 benchmarks • 2 datasets
Latest papers with no code
MOST: Multiple Object localization with Self-supervised Transformers for object discovery
In this work, we present Multiple Object localization with Self-supervised Transformers (MOST) that uses features of transformers trained using self-supervised learning to localize multiple objects in real world images.
DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
This direct connection between the raw features and the clustering objective enables us to implicitly perform classification of the clusters between different graphs, resulting in part semantic segmentation without the need for additional post-processing steps.
Learning from Web Data: the Benefit of Unsupervised Object Localization
In this work, we first systematically study the built-in gap between the web and standard datasets, i. e. different data distributions between the two kinds of data.
Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization
These regions are further refined based on the overlap and similarity ratios.
Iterative Spectral Clustering for Unsupervised Object Localization
This paper addresses the problem of unsupervised object localization in an image.