5 papers · 1 filter
GLASS: Guided Latent Slot Diffusion for Object-Centric Learning
Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth
Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Ye…
DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning
Tobias Lingenberg, Markus Reuter, Gopika Sudhakaran +3
Simple data augmentation techniques, such as rotations and flips, are widely used to enhance the generalization power of computer vision models. However, these techniques often fai…
Benchmarking the Attribution Quality of Vision Models
Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevan…
Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals
Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer +1
Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global semantic categories within an image corpus with…
Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images
Krishnakant Singh, Thanush Navaratnam, Jannik Holmer +2
A long-standing challenge in developing machine learning approaches has been the lack of high-quality labeled data. Recently, models trained with purely synthetic data, here termed…