Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance
This addresses the challenge of robust visual localization and matching in changing environments for applications like autonomous navigation, though it is incremental as it builds on existing dense feature learning methods.
The paper tackles the problem of visual feature representations varying across seasons or times of day by proposing Deja-Vu, a weakly supervised method that learns season-invariant dense features without pixel-wise ground truth, achieving competitive performance in tasks like localization and image retrieval.
"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 does not require pixel-wise ground truth data. The proposed system only requires coarse labels indicating if two images correspond to the same location or not. From these labels, the network is trained to produce "similar" dense feature maps for corresponding locations despite environmental changes. Code will be made available at: https://github.com/jspenmar/DejaVu_Features