Same Features, Different Day: Weakly Supervised Feature Learning For Seasonal Invariance

Abstract

"Like night and day" is a commonly used expression to imply that two things are completely different. Unfortunately, this tends to be the case for current visual feature representations of the same scene across varying seasons or times of day. The aim of this paper is to provide a dense feature representation that can be used to perform localization, sparse matching or image retrieval, regardless of the current seasonal or temporal appearance. Recently, there have been several proposed methodologies for deep learning dense feature representations. These methods make use of ground truth pixel-wise correspondences between pairs of images and focus on the spatial properties of the features. As such, they don't address temporal or seasonal variation. Furthermore, obtaining the required pixel-wise correspondence data to train in cross-seasonal environments is highly complex in most scenarios. We propose Deja-Vu, a weakly supervised approach to learning season invariant features that doe

Stats

• citations20
• S2 citations—
• github stars9
• HF likes0
• heat score11.92
• arxiv keyspencer2020same

Related papers

• Learning Condition Invariant Features For Retrieval-based Localization From 1M Images (2020)0.00
• Self-supervised Modal And View Invariant Feature Learning (2020)0.00
• Image-based Place Recognition On Bucolic Environment Across Seasons From Semantic Edge Description (2019)11.39
• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00
• If-net: An Illumination-invariant Feature Network (2020)6.77
• Learning Aligned Cross-modal Representations From Weakly Aligned Data (2016)14.97
• Adversarial Training For Adverse Conditions: Robust Metric Localisation Using Appearance Transfer (2018)14.43
• Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66