CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition
This addresses robustness issues in visual place recognition for applications like robotics and autonomous systems, representing an incremental improvement over existing methods.
The paper tackles the problem of limited robustness in visual place recognition due to cross-image variations by proposing CricaVPR, a method that uses attention to correlate multiple images and multi-scale adaptation, resulting in outperforming state-of-the-art methods by a large margin with significantly less training time.
Over the past decade, most methods in visual place recognition (VPR) have used neural networks to produce feature representations. These networks typically produce a global representation of a place image using only this image itself and neglect the cross-image variations (e.g. viewpoint and illumination), which limits their robustness in challenging scenes. In this paper, we propose a robust global representation method with cross-image correlation awareness for VPR, named CricaVPR. Our method uses the attention mechanism to correlate multiple images within a batch. These images can be taken in the same place with different conditions or viewpoints, or even captured from different places. Therefore, our method can utilize the cross-image variations as a cue to guide the representation learning, which ensures more robust features are produced. To further facilitate the robustness, we propose a multi-scale convolution-enhanced adaptation method to adapt pre-trained visual foundation models to the VPR task, which introduces the multi-scale local information to further enhance the cross-image correlation-aware representation. Experimental results show that our method outperforms state-of-the-art methods by a large margin with significantly less training time. The code is released at https://github.com/Lu-Feng/CricaVPR.