1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.CV2026
Mask-supervised Object-centric Representation Learning with LeJEPA
Jakob Geusen, Ender Konukoglu
Self-supervised image encoders deliver strong features for downstream tasks but need many images for training. A natural remedy to counter this is to make each image count for more…
cs.CV2022★ 1 cited
Unsupervised Superpixel Generation using Edge-Sparse Embedding
Jakob Geusen, Gustav Bredell, Tianfei Zhou +1
Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and im…