2 papers
cs.CV2025
Weakly Supervised Object Segmentation by Background Conditional Divergence
Hassan Baker, Matthew S. Emigh, Austin J. Brockmeier
As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, rem…
cs.CV2025
Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)
Zhi Li, Hau Phan, Matthew Emigh +1
Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information that is useful for downstream tasks. We hypothesize that the embeddi…