Papers › Global Proxy-based Hard Mining for Visual Place Recognition
Global Proxy-based Hard Mining for Visual Place Recognition
Amar Ali-bey, Brahim Chaib-Draa, Philippe Giguère
Learning deep representations for visual place recognition is commonly performed using pairwise or triple loss functions that highly depend on the hardness of the examples sampled at each training iteration. Existing techniques address this by using computationally and memory expensive offline hard mining, which consists of identifying, at each iteration, the hardest samples from the training set. In this paper we introduce a new technique that performs global hard mini-batch sampling based on proxies. To do so, we add a new end-to-end trainable branch to the network, which generates efficient place descriptors (one proxy for each place). These proxy representations are thus used to construct a global index that encompasses the similarities between all places in the dataset, allowing for highly informative mini-batch sampling at each training iteration. Our method can be used in combination with all existing pairwise and triplet loss functions with negligible additional memory and computation cost. We run extensive ablation studies and show that our technique brings new state-of-the-art performance on multiple large-scale benchmarks such as Pittsburgh, Mapillary-SLS and SPED. In particular, our method provides more than 100% relative improvement on the challenging Nordland dataset. Our code is available at https://github.com/amaralibey/GPM
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 |
|---|---|---|---|---|---|---|---|
| Visual Place Recognition | Mapillary val | NetVLAD (with GPM) | Recall@1 | 82.0 | #14 of 18 | Archive leaderboard | report |
| Visual Place Recognition | Mapillary val | NetVLAD (with GPM) | Recall@10 | 91.4 | #14 of 18 | Archive leaderboard | report |
| Visual Place Recognition | Mapillary val | NetVLAD (with GPM) | Recall@5 | 90.4 | #14 of 18 | Archive leaderboard | report |
| Visual Place Recognition | Nordland | NetVLAD (with GPM) | Recall@1 | 44.9 | #11 of 13 | Archive leaderboard | report |
| Visual Place Recognition | Nordland | NetVLAD (with GPM) | Recall@5 | 50.2 | #11 of 13 | Archive leaderboard | report |
| Visual Place Recognition | Pittsburgh-250k-test | NetVLAD (with GPM) | Recall@1 | 91.5 | #12 of 13 | Archive leaderboard | report |
| Visual Place Recognition | Pittsburgh-250k-test | NetVLAD (with GPM) | Recall@10 | 98.1 | #12 of 13 | Archive leaderboard | report |
| Visual Place Recognition | Pittsburgh-250k-test | NetVLAD (with GPM) | Recall@5 | 97.2 | #12 of 13 | 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