activity
20242026
collaborators
Showing 2025Show all

6 papers · 1 filter

cs.CV2025

Removing Cost Volumes from Optical Flow Estimators

Simon Kiefhaber, Stefan Roth, Simone Schaub-Meyer

Cost volumes are used in every modern optical flow estimator, but due to their computational and space complexity, they are often a limiting factor regarding both processing speed…

cs.CV2025

ART: Adaptive Relation Tuning for Generalized Relation Prediction

Gopika Sudhakaran, Hikaru Shindo, Patrick Schramowski +3

Visual relation detection (VRD) is the task of identifying the relationships between objects in a scene. VRD models trained solely on relation detection data struggle to generalize…

cs.CV2025

Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation

Dustin Carrión-Ojeda, Stefan Roth, Simone Schaub-Meyer

Few-shot classification and segmentation (FS-CS) focuses on jointly performing multi-label classification and multi-class segmentation using few annotated examples. Although the cu…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

Disentangling Polysemantic Channels in Convolutional Neural Networks

Robin Hesse, Jonas Fischer, Simone Schaub-Meyer +1

Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mec…