ViCE: Visual Concept Embedding Discovery and Superpixelization. (arXiv:2111.12460v2 [cs.CV] UPDATED)

Recent self-supervised computer vision methods have demonstrated equal or
better performance to supervised methods, opening for AI systems to learn
visual representations from practically unlimited data. However, these methods
are classification-based and thus ineffective for learning dense feature maps
required for unsupervised semantic segmentation. This work presents a method to
effectively learn dense semantically rich visual concept embeddings applicable
to high-resolution images. We introduce superpixelization as a means to
decompose images into a small set of visually coherent regions, allowing …

arxiv concept cv discovery embedding