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...
Autors principals: | Zhang, F, Torr, P, Ranftl, R, Richter, S |
---|---|
Format: | Conference item |
Idioma: | English |
Publicat: |
Neural Information Processing Systems Foundation
2021
|
Ítems similars
-
Open vocabulary semantic segmentation with Patch Aligned Contrastive Learning
per: Mukhoti, J, et al.
Publicat: (2023) -
Scalable cascade inference for semantic image segmentation
per: Sturgess, P, et al.
Publicat: (2012) -
Dense semantic image segmentation with objects and attributes
per: Zheng, S, et al.
Publicat: (2014) -
Pyramid Context Contrast for Semantic Segmentation
per: Yuzhong Chen, et al.
Publicat: (2019-01-01) -
Highly Contrast Image Correction for Dim Boundary Separation of Image Semantic Segmentation
per: Jinyeob Choi, et al.
Publicat: (2021-01-01)