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