Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition
This addresses the need for real-time, efficient Seq-VPR systems in robotics and autonomous vehicles, though it is incremental as it builds on existing transformer methods.
The paper tackled the problem of sequential visual place recognition by proposing Adapt-STformer, which improves flexibility and efficiency, achieving up to 17% higher recall, 36% faster sequence extraction, and 35% lower memory usage compared to baselines.
Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively; however, existing approaches prioritize performance at the expense of flexibility and efficiency. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq-length), deliver fast inference, and have low memory usage to meet real-time constraints. To our knowledge, no existing transformer-based Seq-VPR method achieves both flexibility and efficiency. To address this gap, we propose Adapt-STformer, a Seq-VPR method built around our novel Recurrent Deformable Transformer Encoder (Recurrent-DTE), which uses an iterative recurrent mechanism to fuse information from multiple sequential frames. This design naturally supports variable seq-lengths, fast inference, and low memory usage. Experiments on the Nordland, Oxford, and NuScenes datasets show that Adapt-STformer boosts recall by up to 17% while reducing sequence extraction time by 36% and lowering memory usage by 35% compared to the second-best baseline.