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...
主要な著者: | Zhang, F, Torr, P, Ranftl, R, Richter, S |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Neural Information Processing Systems Foundation
2021
|
類似資料
-
Open vocabulary semantic segmentation with Patch Aligned Contrastive Learning
著者:: Mukhoti, J, 等
出版事項: (2023) -
Scalable cascade inference for semantic image segmentation
著者:: Sturgess, P, 等
出版事項: (2012) -
Dense semantic image segmentation with objects and attributes
著者:: Zheng, S, 等
出版事項: (2014) -
Pyramid Context Contrast for Semantic Segmentation
著者:: Yuzhong Chen, 等
出版事項: (2019-01-01) -
Highly Contrast Image Correction for Dim Boundary Separation of Image Semantic Segmentation
著者:: Jinyeob Choi, 等
出版事項: (2021-01-01)