Curriculum Learning for Recurrent Video Object Segmentation

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/.

READ FULL TEXT
research
11/02/2018

An Empirical Exploration of Curriculum Learning for Neural Machine Translation

Machine translation systems based on deep neural networks are expensive ...
research
02/28/2023

One-Shot Video Inpainting

Recently, removing objects from videos and filling in the erased regions...
research
09/03/2019

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

The paper explores a novel methodology in source code obfuscation throug...
research
07/20/2020

TENet: Triple Excitation Network for Video Salient Object Detection

In this paper, we propose a simple yet effective approach, named Triple ...
research
11/29/2018

Progressive Recurrent Learning for Visual Recognition

Computer vision is difficult, partly because the mathematical function c...
research
10/10/2020

Hybrid Sequence to Sequence Model for Video Object Segmentation

One-shot Video Object Segmentation (VOS) is the task of pixel-wise track...
research
05/28/2021

AutoSampling: Search for Effective Data Sampling Schedules

Data sampling acts as a pivotal role in training deep learning models. H...

Please sign up or login with your details

Forgot password? Click here to reset