[HTML][HTML] Multimodal Contrastive Learning for Remote Sensing Image Feature Extraction Based on Relaxed Positive Samples
Z Zhang, Q Li, W **g, G He, L Zhu, S Gao - Sensors, 2024 - mdpi.com
Traditional multimodal contrastive learning brings text and its corresponding image closer
together as a positive pair, where the text typically consists of fixed sentence structures or …
together as a positive pair, where the text typically consists of fixed sentence structures or …
[PDF][PDF] FreeMix: Open Vocabulary Domain Generalization of Remote Sensing Images for Semantic Segmentation
J Wu, J Shi, Z Zhao, Z Liu, R Zhi - 2025 - preprints.org
In this study, we present a novel concept termed open vocabulary domain generalization
(OVDG), which we investigate within the context of semantic segmentation. OVDG presents …
(OVDG), which we investigate within the context of semantic segmentation. OVDG presents …