8 papers
OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment
Tianchao Li, Shujian Yu, Xinrui Zu +4
Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively underexplored. Pairwise CLIP-st…
NOFE - Neural Operator Function Embedding
Lars Uebbing, Harald L. Joakimsen, Siyan Chen +6
Most dimensionality reduction methods treat data as discrete point clouds, ignoring the continuous domain structure inherent to many real-world processes. To bridge this gap, we in…
WindINR: Latent-State INR for Fast Local Wind Query and Correction in Complex Terrain
Yi Xiao, Qilong Jia, Hang Fan +4
Many downstream decisions in complex terrain require fast wind estimates at a small number of user-specified locations and heights for a given forecast valid time, rather than anot…
Random Window Augmentations for Deep Learning Robustness in CT and Liver Tumor Segmentation
Eirik A. Ãstmo, Kristoffer K. Wickstrøm, Keyur Radiya +3
Contrast-enhanced Computed Tomography (CT) is important for diagnosis and treatment planning for various medical conditions. Deep learning (DL) based segmentation models may enable…
FLEXtime: Filterbank learning to explain time series
Thea Brüsch, Kristoffer K. Wickstrøm, Mikkel N. Schmidt +2
State-of-the-art methods for explaining predictions from time series involve learning an instance-wise saliency mask for each time step; however, many types of time series are diff…
From Colors to Classes: Emergence of Concepts in Vision Transformers
Teresa Dorszewski, Lenka TÄtková, Robert Jenssen +2
Vision Transformers (ViTs) are increasingly utilized in various computer vision tasks due to their powerful representation capabilities. However, it remains understudied how ViTs p…