3

Integrating Prior Knowledge in Contrastive Learning with Kernel
Data augmentation is a crucial component in unsupervised contrastive learning (CL). It determines how positive samples are defined and, …
PDF Cite
LSVL: Large-scale season-invariant visual localization for UAVs
Localization of autonomous unmanned aerial vehicles (UAVs) relies heavily on Global Navigation Satellite Systems (GNSS), which are …
PDF Cite
REM: Routing Entropy Minimization for Capsule Networks
Capsule Networks ambition is to build an explainable and biologically-inspired neural network model. One of their main innovations …
PDF Cite
Unsupervised Learning of Unbiased Visual Representations
Deep neural networks are known for their inability to learn robust representations when biases exist in the dataset. This results in a …
PDF Cite