Excavate Condition-invariant Space by Intrinsic Encoder

TL;DR

This paper introduces a semi-supervised intrinsic encoder that learns a condition-invariant latent space for place recognition, effectively handling drastic appearance changes due to weather, seasons, and lighting, and outperforms existing methods.

Contribution

The paper proposes a novel semi-supervised intrinsic encoder that excavates condition-invariant features using unpaired data, improving long-term place recognition under environmental variations.

Findings

Achieves state-of-the-art performance on Nordland benchmark.

Effectively handles drastic appearance changes in place recognition.

Outperforms previous image-level recognition methods.

Abstract

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 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 be employed to 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 and semantic information by proposed self-supervised encoder loss. 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 and show that our semi-supervised intrinsic encoder achieves remarkable performance for place recognition under drastic appearance changes. The proposed intrinsic encoder outperforms the state-of-the-art image-level place recognition methods on standard benchmark Nordland.