Curriculum Learning for Recurrent Video Object Segmentation

by   Maria Gonzalez-i-Calabuig, et al.

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


An Empirical Exploration of Curriculum Learning for Neural Machine Translation

Machine translation systems based on deep neural networks are expensive ...

RVOS: End-to-End Recurrent Network for Video Object Segmentation

Multiple object video object segmentation is a challenging task, special...

DeepObfusCode: Source Code Obfuscation Through Sequence-to-Sequence Networks

The paper explores a novel methodology in source code obfuscation throug...

TENet: Triple Excitation Network for Video Salient Object Detection

In this paper, we propose a simple yet effective approach, named Triple ...

Progressive Recurrent Learning for Visual Recognition

Computer vision is difficult, partly because the mathematical function c...

Hybrid Sequence to Sequence Model for Video Object Segmentation

One-shot Video Object Segmentation (VOS) is the task of pixel-wise track...

CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance

We introduce CASED, a novel curriculum sampling algorithm that facilitat...

Code Repositories


Curriculum Learning for Recurrent Video Object Segmentation

view repo