Cluster-based Curriculum Learning for Vision-and-Language Navigation
Lists
Only you see this
Abstract
The vision-and-language navigation (VLN) task requires the agent to navigate by following both natural language instructions and vision. Prior works focus on improving the navigation model or adopting data augmentation to enhance the accuracy and efficiency of navigation. However, few attempts have been made to optimize the training process. In this paper, we propose a cluster-based curriculum learning (CCL) method to schedule appropriate curricula to acquire a more rational learning process. Our CCL dynamically segments the tasks in training dataset into three subsets: easy, medium and hard, according to whether tasks can be successfully completed by the present navigation model. Meanwhile, we propose a dynamic data extraction method based on the volume of subsets to adjust the priority of training from easy to hard. On the other hand, the existing metrics are hard to show the possibility that the agent will complete the task exactly along the expected path. We propose a new metric named path success rate (PSR), where a path is defined as success when the agent passes by all locations described by the instruction. Extensive experiments are conducted to demonstrate the effectiveness and superiority of our proposed CCL on VLN tasks.
BibTeX
@inproceedings{wang2022cluster,
author = {Ting Wang and Zongkai Wu and Zihan Liu and Donglin Wang},
title = {{Cluster-based Curriculum Learning for Vision-and-Language Navigation}},
booktitle = {IJCNN},
year = {2022},
url = {https://openreview.net/forum?id=FfbZp5oe47},
}Loading related content...