Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual Localization
This work addresses the problem of robust visual localization for mobile robots and autonomous driving in dynamic environments, presenting an incremental improvement with new loss functions and a coarse-to-fine pipeline.
The paper tackles retrieval-based visual localization under varying environmental conditions by proposing a domain-invariant feature extraction method and a novel gradient-weighted similarity activation mapping loss, achieving performance on par with or better than state-of-the-art baselines in medium to high precision, especially in challenging scenarios like illumination changes and night-time images.
Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of environmental conditions, e.g. illumination, seasonal and weather changes, retrieval-based visual localization is severely affected and becomes a challenging problem. In this work, a general architecture is first formulated probabilistically to extract domain invariant feature through multi-domain image translation. And then a novel gradient-weighted similarity activation mapping loss (Grad-SAM) is incorporated for finer localization with high accuracy. We also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised manner. The final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models without and with Grad-SAM loss. Extensive experiments have been conducted to validate the effectiveness of the proposed approach on the CMUSeasons dataset. The strong generalization ability of our approach is verified on RobotCar dataset using models pre-trained on urban part of CMU-Seasons dataset. Our performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision, especially under the challenging environments with illumination variance, vegetation and night-time images. The code and pretrained models are available on https://github.com/HanjiangHu/DISAM.