Looking beyond single images for contrastive semantic segmentation learning
We present an approach to contrastive representation learning for semantic segmentation. Our approach leverages the representational power of existing feature extractors to find corresponding regions across images. These cross-image correspondences are used as auxiliary labels to guide the pixel-lev...
| Hoofdauteurs: | , , , |
|---|---|
| Formaat: | Conference item |
| Taal: | English |
| Gepubliceerd in: |
Neural Information Processing Systems Foundation
2021
|