Papers › STIR: Siamese Transformer for Image Retrieval Postprocessing

STIR: Siamese Transformer for Image Retrieval Postprocessing

26 Apr 2023arXiv:2304.13393archive 2025-07-28

Aleksei Shabanov, Aleksei Tarasov, Sergey Nikolenko

Current metric learning approaches for image retrieval are usually based on learning a space of informative latent representations where simple approaches such as the cosine distance will work well. Recent state of the art methods such as HypViT move to more complex embedding spaces that may yield better results but are harder to scale to production environments. In this work, we first construct a simpler model based on triplet loss with hard negatives mining that performs at the state of the art level but does not have these drawbacks. Second, we introduce a novel approach for image retrieval postprocessing called Siamese Transformer for Image Retrieval (STIR) that reranks several top outputs in a single forward pass. Unlike previously proposed Reranking Transformers, STIR does not rely on global/local feature extraction and directly compares a query image and a retrieved candidate on pixel level with the usage of attention mechanism. The resulting approach defines a new state of the art on standard image retrieval datasets: Stanford Online Products and DeepFashion In-shop. We also release the source code at https://github.com/OML-Team/open-metric-learning/tree/main/pipelines/postprocessing/ and an interactive demo of our approach at https://dapladoc-oml-postprocessing-demo-srcappmain-pfh2g0.streamlit.app/

PaperPDFCode

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

Image RetrievalMetric LearningRe-RankingRepresentation LearningRerankingRetrieval

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Metric Learning In-Shop STIR R@1 95 #2 of 15 Archive leaderboard report
Metric Learning In-Shop ViT-Triplet R@1 92.1 #9 of 15 Archive leaderboard report
Metric Learning Stanford Online Products STIR R@1 88.3 #2 of 33 Archive leaderboard report
Metric Learning Stanford Online Products ViT-Triplet R@1 86.5 #4 of 33 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

Absolute Position EncodingsAdamAttentionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSiamese NetworkTransformerTriplet Loss

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