1 citations · 1 across the 2 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Object-centric LeJEPA
Jakob Geusen, Ender Konukoglu
Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets.…
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…