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...
Hlavní autoři: | Zhang, F, Torr, P, Ranftl, R, Richter, S |
---|---|
Médium: | Conference item |
Jazyk: | English |
Vydáno: |
Neural Information Processing Systems Foundation
2021
|
Podobné jednotky
-
Open vocabulary semantic segmentation with Patch Aligned Contrastive Learning
Autor: Mukhoti, J, a další
Vydáno: (2023) -
Scalable cascade inference for semantic image segmentation
Autor: Sturgess, P, a další
Vydáno: (2012) -
Dense semantic image segmentation with objects and attributes
Autor: Zheng, S, a další
Vydáno: (2014) -
Pyramid Context Contrast for Semantic Segmentation
Autor: Yuzhong Chen, a další
Vydáno: (2019-01-01) -
Highly Contrast Image Correction for Dim Boundary Separation of Image Semantic Segmentation
Autor: Jinyeob Choi, a další
Vydáno: (2021-01-01)