6 papers · 1 filter
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Markus Karmann, Shile Li, Christian Internò +10
Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA train…
Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation
Shile Li, Markus Karmann, Onay Urfalioglu
We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wis…
M2N2V2: Multi-Modal Unsupervised and Training-free Interactive Segmentation
Markus Karmann, Peng-Tao Jiang, Bo Li +1
We present Markov Map Nearest Neighbor V2 (M2N2V2), a novel and simple, yet effective approach which leverages depth guidance and attention maps for unsupervised and training-free…
MLV-Net: Rater-Based Majority-Label Voting for Consistent Meningeal Lymphatic Vessel Segmentation
Fabian Bongratz, Markus Karmann, Adrian Holz +9
Meningeal lymphatic vessels (MLVs) are responsible for the drainage of waste products from the human brain. An impairment in their functionality has been associated with aging as w…
Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation
Markus Karmann, Onay Urfalioglu
Recent progress in interactive point prompt based Image Segmentation allows to significantly reduce the manual effort to obtain high quality semantic labels. State-of-the-art unsup…
Looking Beyond Corners: Contrastive Learning of Visual Representations for Keypoint Detection and Description Extraction
Henrique Siqueira, Patrick Ruhkamp, Ibrahim Halfaoui +2
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual rep…