Can I read YOLOR for Multi-Task Learning in Vision on EtoBox?

YOLOR for Multi-Task Learning in Vision by npkhang7264 is a document available to read on EtoBox.

What is YOLOR for Multi-Task Learning in Vision about?

This paper presents a novel multi-task learning (MTL) framework based on the YOLOR architecture, which aims to jointly train multiple vision tasks such as object detection, instance segmentation, semantic segmentation, and image captioning. The authors propose strategies to maximize shared semantic information while minimizing conflicts between tasks, achieving competitive performance with a low parameter count and without pre-training. Key contributions include a focus on semantic consistency in data augme

Author

npkhang7264

Language

EN