Excavate Condition-invariant Space by Intrinsic Encoder

06/29/2018
by   Jian Xu, et al.
0

As the human, we can recognize the places across a wide range of changing environmental conditions such as those caused by weathers, seasons, and day-night cycles. We can excavate and memorize the stable semantic structure of different places and scenes. For example, we can recognize tree whether the bare tree in winter or lush tree in summer. Therefore, the intrinsic features that are corresponding to specific semantic contents and condition-invariant of appearance changes can improve the performance of long-term place recognition significantly. In this paper, we propose a novel intrinsic encoder that excavates the condition-invariant latent space of different places under drastic appearance changes. Our method excavates the space of intrinsic structure features by self-supervised cycle loss designed based on Generative Adversarial Network (GAN). Different from previous learning based place recognition methods that need paired training data of each place with appearance changes, we employ the weakly-supervised strategy to utilize unpaired set-based training data of different environmental conditions. We conduct comprehensive experiments on the standard datasets and show that our semi-supervised intrinsic encoder achieves excellent performance for place recognition under drastic appearance changes.

READ FULL TEXT
research
03/04/2023

Self-Supervised Learning for Biologically-Inspired Place Representation Generalization across Appearance Changes

Visual place recognition is a key to unlocking spatial navigation for an...
research
05/27/2021

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

We present a method for localizing a single camera with respect to a poi...
research
12/24/2020

Appearance-Invariant 6-DoF Visual Localization using Generative Adversarial Networks

We propose a novel visual localization network when outside environment ...
research
01/24/2020

Unsupervised Learning Methods for Visual Place Recognition in Discretely and Continuously Changing Environments

Visual place recognition in changing environments is the problem of find...
research
01/16/2018

Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition

When a human drives a car along a road for the first time, they later re...
research
02/25/2019

Condition-Invariant Multi-View Place Recognition

Visual place recognition is particularly challenging when places suffer ...
research
04/04/2018

Representing Videos based on Scene Layouts for Recognizing Agent-in-Place Actions

We address the recognition of agent-in-place actions, which are associat...

Please sign up or login with your details

Forgot password? Click here to reset