1. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics;kendall;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,0
2. Rotograd: Gradient homogenization in multitask learning;javaloy;International Conference on Learning Representations,0
3. DeepGCNs: Can GCNs Go As Deep As CNNs?
4. Learning Multiple Pixelwise Tasks Based on Loss Scale Balancing
5. H3dnet: 3d object detection using hybrid geometric primitives;zhang;European Conference on Computer Vision,0