Papers › Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
Xuanmeng Zhang, Minyue Jiang, Zhedong Zheng, Xiao Tan, Errui Ding, Yi Yang
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Drone-view target localization | University-1652 | GNN-Reranking | AP | 74.11 | #9 of 11 | Archive leaderboard | report |
| Drone-view target localization | University-1652 | GNN-Reranking | Recall@1 | 70.3 | #9 of 11 | Archive leaderboard | report |
| Image Retrieval | Oxford5k | GNN-Reranking | mAP | 92.95 | #1 of 2 | Archive leaderboard | report |
| Image Retrieval | Paris6k | GNN-Reranking | mAP | 96.21 | #2 of 2 | Archive leaderboard | report |
| Person Re-Identification | Market-1501 | GNN-Reranking | Rank-1 | 96.11 | #26 of 135 | Archive leaderboard | report |
| Person Re-Identification | Market-1501 | GNN-Reranking | mAP | 94.65 | #26 of 135 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections