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