CVMay 12, 2024

BoQ: A Place is Worth a Bag of Learnable Queries

arXiv:2405.07364v379 citationsh-index: 39Has CodeCVPR
Originality Highly original
AI Analysis

This addresses the problem of accurate location identification in computer vision for applications like robotics and autonomous systems, representing a strong incremental improvement with novel method elements.

The paper tackles the challenge of visual place recognition under varying conditions by introducing Bag-of-Queries (BoQ), a method that learns global queries to capture place-specific attributes, resulting in consistent outperformance of state-of-the-art techniques across 14 benchmarks while being orders of magnitude faster.

In visual place recognition, accurately identifying and matching images of locations under varying environmental conditions and viewpoints remains a significant challenge. In this paper, we introduce a new technique, called Bag-of-Queries (BoQ), which learns a set of global queries designed to capture universal place-specific attributes. Unlike existing methods that employ self-attention and generate the queries directly from the input features, BoQ employs distinct learnable global queries, which probe the input features via cross-attention, ensuring consistent information aggregation. In addition, our technique provides an interpretable attention mechanism and integrates with both CNN and Vision Transformer backbones. The performance of BoQ is demonstrated through extensive experiments on 14 large-scale benchmarks. It consistently outperforms current state-of-the-art techniques including NetVLAD, MixVPR and EigenPlaces. Moreover, as a global retrieval technique (one-stage), BoQ surpasses two-stage retrieval methods, such as Patch-NetVLAD, TransVPR and R2Former, all while being orders of magnitude faster and more efficient. The code and model weights are publicly available at https://github.com/amaralibey/Bag-of-Queries.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes