Search Results for author:
Found 4 papers, 1 papers with code
A Survey of Heterogeneous Transfer Learning
These methods typically presuppose identical feature spaces and label spaces in both domains, known as homogeneous transfer learning, which, however, is not always a practical assumption.
Sampling Through the Lens of Sequential Decision Making
Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation.
Self-supervised Learning with Fully Convolutional Networks
By learning to solve a Jigsaw Puzzle problem with 25 patches and transferring the learned features to semantic segmentation task on Cityscapes dataset, we achieve a 5. 8 percentage point improvement over the baseline model that initialized from random values.
Real time backbone for semantic segmentation
The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
