Visual Memorability for Robotic Interestingness via Unsupervised Online Learning

TL;DR

This paper introduces a novel unsupervised online learning system for robotic scene interestingness prediction, combining translation-invariant visual memory with a three-stage architecture to improve accuracy in autonomous exploration tasks.

Contribution

It presents a new translation-invariant visual memory and a three-stage learning architecture for robotic scene interestingness prediction, enabling online adaptation and higher accuracy.

Findings

Achieves higher accuracy than state-of-the-art methods on robotic interestingness datasets.

Effectively combines long-term, short-term, and online learning for scene understanding.

Demonstrates practical applicability in autonomous exploration scenarios.

Abstract

In this paper, we explore the problem of interesting scene prediction for mobile robots. This area is currently underexplored but is crucial for many practical applications such as autonomous exploration and decision making. Inspired by industrial demands, we first propose a novel translation-invariant visual memory for recalling and identifying interesting scenes, then design a three-stage architecture of long-term, short-term, and online learning. This enables our system to learn human-like experience, environmental knowledge, and online adaption, respectively. Our approach achieves much higher accuracy than the state-of-the-art algorithms on challenging robotic interestingness datasets.