Placeformer: Transformer-based Visual Place Recognition Using Multi-scale Patch Selection And Fusion

Abstract

Visual place recognition is a challenging task in the field of computer vision, and autonomous robotics and vehicles, which aims to identify a location or a place from visual inputs. Contemporary methods in visual place recognition employ convolutional neural networks and utilize every region within the image for the place recognition task. However, the presence of dynamic and distracting elements in the image may impact the effectiveness of the place recognition process. Therefore, it is meaningful to focus on task-relevant regions of the image for improved recognition. In this paper, we present PlaceFormer, a novel transformer-based approach for visual place recognition. PlaceFormer employs patch tokens from the transformer to create global image descriptors, which are then used for image retrieval. To re-rank the retrieved images, PlaceFormer merges the patch tokens from the transformer to form multi-scale patches. Utilizing the transformer's self-attention mechanism, it selects pat

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keykannan2024placeformer

Related papers

• \(r^{2}\)former: Unified \(r\)etrieval And \(r\)eranking Transformer For Place Recognition (2023)18.31
• Towards Implicit Aggregation: Robust Image Representation For Place Recognition In The Transformer Era (2025)3.09
• Regressing Transformers For Data-efficient Visual Place Recognition (2024)3.58
• Spatio-semantic Convnet-based Visual Place Recognition (2019)10.21
• Fast, Compact And Highly Scalable Visual Place Recognition Through Sequence-based Matching Of Overloaded Representations (2020)9.41
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• City-scale Visual Place Recognition With Deep Local Features Based On Multi-scale Ordered VLAD Pooling (2020)1.69
• Boosting Vision Transformers For Image Retrieval (2022)15.28