# Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation

Source: [Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation](<https://www.sota2.com/research/paper/68fa6a721e209131cea282bd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:25:36.663Z

Authors: Yihao Zhang, John J. Leonard

Published: 2021-03-19T21:28:58.000Z

## Abstract

For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system is initially bootstrapped with supervised training on a labeled dataset and we look for a self-supervised training method that can subsequently improve the system over the supervised training baseline using only unlabeled data. In this work, we leverage temporal consistency between frames in monocular video to perform this bootstrapped self-supervised training. We show that a well-trained state-of-the-art semantic segmentation network can be further improved through our method. In addition, we show that the bootstrapped self-supervised training framework can help a network learn depth estimation better than pure supervised training or self-supervised training.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.11031>)

[PDF](<https://arxiv.org/pdf/2103.11031.pdf>)