Curriculum Learning for Recurrent Video Object Segmentation
This work addresses video object segmentation for applications like autonomous driving, but it is incremental as it focuses on optimizing training strategies for an existing recurrent method.
The paper tackled video object segmentation by applying curriculum learning strategies to a recurrent architecture, finding that inverse schedule sampling outperforms forward sampling and progressive frame skipping is beneficial only when using ground truth masks, achieving improved performance on the KITTI-MOTS car class.
Video object segmentation can be understood as a sequence-to-sequence task that can benefit from the curriculum learning strategies for better and faster training of deep neural networks. This work explores different schedule sampling and frame skipping variations to significantly improve the performance of a recurrent architecture. Our results on the car class of the KITTI-MOTS challenge indicate that, surprisingly, an inverse schedule sampling is a better option than a classic forward one. Also, that a progressive skipping of frames during training is beneficial, but only when training with the ground truth masks instead of the predicted ones. Source code and trained models are available at http://imatge-upc.github.io/rvos-mots/.