A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors

TL;DR

This paper introduces A2GC-VPR, an innovative asymmetric aggregation method with geometric constraints that improves visual place recognition by better handling distributional differences and spatial relationships in image features.

Contribution

It proposes a novel asymmetric aggregation approach with geometric constraints for locally aggregated descriptors, addressing limitations of symmetric optimal transport methods.

Findings

Outperforms state-of-the-art methods on MSLS, NordLand, and Pittsburgh datasets.

Enhances matching accuracy and robustness in visual place recognition.

Effectively handles distributional discrepancies and spatial relationships in features.

Abstract

Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from deep backbones to form global descriptors. Optimal transport-based aggregation methods reformulate feature-to-cluster assignment as a transport problem, but the standard Sinkhorn algorithm symmetrically treats source and target marginals, limiting effectiveness when image features and cluster centers exhibit substantially different distributions. We propose an asymmetric aggregation VPR method with geometric constraints for locally aggregated descriptors, called $A^2$GC-VPR. Our method employs row-column normalization averaging with separate marginal calibration, enabling asymmetric matching that adapts to distributional discrepancies in visual place recognition. Geometric constraints are incorporated through learnable coordinate embeddings, computing compatibility scores fused with feature similarities, thereby promoting spatially proximal features to the same cluster and enhancing spatial awareness. Experimental results on MSLS, NordLand, and Pittsburgh datasets demonstrate superior performance, validating the effectiveness of our approach in improving matching accuracy and robustness.