-
C-BEV: Contrastive Bird’s Eye View Training for Cross-View Image Retrieval an...
The CVUSA and CVACT datasets are used for cross-view geolocalization. The VIGOR dataset is used for cross-view image retrieval and 3-DoF pose estimation. -
ICPC: Instance-Conditioned Prompting with Contrastive Learning for Semantic S...
Semantic segmentation is a fundamental task in computer vision and has witnessed great progress using deep learning in the past few years. It aims at segmenting things or stuff... -
ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose C...
Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising -
Contrastive learning of global and local features for medical image segmentation
A dataset for medical image segmentation with limited annotations -
A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representations.
