Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective

by   Xuanmeng Zhang, et al.

The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw of re-ranking, i.e., high computational complexity, which leads to an unaffordable time cost for real-world applications. In this paper, we revisit re-ranking and demonstrate that re-ranking can be reformulated as a high-parallelism Graph Neural Network (GNN) function. In particular, we divide the conventional re-ranking process into two phases, i.e., retrieving high-quality gallery samples and updating features. We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph. In practice, GNN only needs to concern vertices with the connected edges. Since the graph is sparse, we can efficiently update the vertex features. On the Market-1501 dataset, we accelerate the re-ranking processing from 89.2s to 9.4ms with one K40m GPU, facilitating the real-time post-processing. Similarly, we observe that our method achieves comparable or even better retrieval results on the other four image retrieval benchmarks, i.e., VeRi-776, Oxford-5k, Paris-6k and University-1652, with limited time cost. Our code is publicly available.


page 1

page 2

page 3

page 4


Graph Convolution Based Efficient Re-Ranking for Visual Retrieval

Visual retrieval tasks such as image retrieval and person re-identificat...

Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval

Fabric image retrieval is beneficial to many applications including clot...

RankDNN: Learning to Rank for Few-shot Learning

This paper introduces a new few-shot learning pipeline that casts releva...

Attentional Graph Neural Network for Parking-slot Detection

Deep learning has recently demonstrated its promising performance for vi...

A Review on Graph Neural Network Methods in Financial Applications

Keeping the individual features and the complicated relations, graph dat...

Three Tiers Neighborhood Graph and Multi-graph Fusion Ranking for Multi-feature Image Retrieval: A Manifold Aspect

Single feature is inefficient to describe content of an image, which is ...

Ranking-aware Uncertainty for Text-guided Image Retrieval

Text-guided image retrieval is to incorporate conditional text to better...

Please sign up or login with your details

Forgot password? Click here to reset