Multi-Condition Place Generator for Robust Place Recognition

Yiting Cheng, Yankai Wang, Lizhe Qi, Wenqiang Zhang

International Conference on Multimedia Modeling (MMM 2019) (CCF C)

As an image retrieval task, visual place recognition (VPR) encounters two technical challenges: appearance variations resulted from external environment changes and the lack of cross-domain paired training data. To overcome these challenges, multi-condition place generator (MPG) is introduced for data generation. The objective of MPG is two-fold, (1) synthesizing realistic place samples corresponding to multiple conditions; (2) preserving the place identity information during the generation procedure. While MPG smooths the appearance disparities under various conditions, it also suffers image distortion. For this reason, we propose the relative quality based triplet (RQT) loss by reshaping the standard triplet loss such that it down-weights the loss assigned to low-quality images. By taking advantage of the innovations mentioned above, a condition-invariant VPR model is trained without the labeled training data. Comprehensive experiments show that our method outperforms state-of-the-art algorithms by a large margin on several challenging benchmarks.