CAHIR: Co-Attentive Hierarchical Image Representations for Visual Place Recognition
Guohao Peng,Heshan Li,Yifeng Huang,Jun Zhang,Mingxing Wen,Singh Rahul,Danwei Wang,Guohao Peng,Heshan Li,Yifeng Huang,Jun Zhang,Mingxing Wen,Singh Rahul,Danwei Wang
Robust visual place recognition (VPR) against significant appearance changes is crucial for the life-long operation of mobile robots. Focusing on this task, we propose a Co-Attentive Hierarchical Image Representations (CAHIR) framework for VPR, which unifies attention-sharing global and local descriptor generation into one encoding pipeline. The hierarchical descriptors are applied to a coarse-to-...
