Datasets › Stanford Online Products

Stanford Online Products

Introduced by Hyun Oh Song et al. in Deep Metric Learning via Lifted Structured Feature Embedding1 Jan 2016 archive 2025-07-28

Stanford Online Products (SOP) dataset has 22,634 classes with 120,053 product images. The first 11,318 classes (59,551 images) are split for training and the other 11,316 (60,502 images) classes are used for testing

Source: Deep Metric Learning with Alternating Projections onto Feasible Sets Image Source: https://cvgl.stanford.edu/projects/lifted_struct/

Benchmarks archive 2025-07-28

All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

30 shown of 40 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 231. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Center Contrastive Loss for Metric Learning 0 1 1 Aug 2023 not harvested
STIR: Siamese Transformer for Image Retrieval Postprocessing 1 2 26 Apr 2023 not harvested
Unicom: Universal and Compact Representation Learning for Image Retrieval 3 2 12 Apr 2023 ran 3 of 6 samples (3 unverified; 6 pointer-only for licence)
MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset 1 1 22 Mar 2023 ran 0 of 2 samples (2 unverified)
A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems 1 1 15 Sep 2022 not harvested
DAS: Densely-Anchored Sampling for Deep Metric Learning 1 1 30 Jul 2022 ran 0 of 1 samples (1 unverified)
Hierarchical Average Precision Training for Pertinent Image Retrieval 2 2 5 Jul 2022 ran 6 of 9 samples (3 unverified)
Attributable Visual Similarity Learning 1 1 28 Mar 2022 ran 0 of 4 samples (4 unverified)
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning 2 2 21 Mar 2022 ran 4 of 6 samples (2 unverified)
Non-isotropy Regularization for Proxy-based Deep Metric Learning 1 1 16 Mar 2022 ran 0 of 3 samples (3 unverified)
Integrating Language Guidance into Vision-based Deep Metric Learning 1 1 16 Mar 2022 ran 0 of 5 samples (5 unverified)
Dissecting the impact of different loss functions with gradient surgery 0 1 27 Jan 2022 not harvested
Cross Modal Retrieval with Querybank Normalisation 1 1 23 Dec 2021 ran 2 of 3 samples (1 unverified)
Robust and Decomposable Average Precision for Image Retrieval 1 4 1 Oct 2021 ran 4 of 5 samples (1 unverified)
Recall@k Surrogate Loss with Large Batches and Similarity Mixup 2 3 25 Aug 2021 ran 0 of 11 samples (11 unverified)
Towards Interpretable Deep Metric Learning with Structural Matching 1 1 12 Aug 2021 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
It Takes Two to Tango: Mixup for Deep Metric Learning 1 1 9 Jun 2021 ran 2 of 2 samples (0 unverified)
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough 2 1 9 Feb 2021 not harvested
Grafit: Learning fine-grained image representations with coarse labels 0 1 25 Nov 2020 not harvested
S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning 1 1 17 Sep 2020 ran 0 of 3 samples (3 unverified)
Hard negative examples are hard, but useful 1 1 24 Jul 2020 not harvested
Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval 2 1 23 Jul 2020 ran 2 of 2 samples (0 unverified)
Calibrated neighborhood aware confidence measure for deep metric learning 0 1 8 Jun 2020 not harvested
DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning 2 1 28 Apr 2020 ran 2 of 5 samples (3 unverified; 3 pointer-only for licence)
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis 1 2 2 Apr 2020 ran 0 of 5 samples (5 unverified)
Proxy Anchor Loss for Deep Metric Learning 3 1 31 Mar 2020 not harvested
PADS: Policy-Adapted Sampling for Visual Similarity Learning 1 1 24 Mar 2020 ran 0 of 10 samples (10 unverified)
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses 1 1 19 Mar 2020 ran 1 of 1 samples (0 unverified)
Circle Loss: A Unified Perspective of Pair Similarity Optimization 16 1 25 Feb 2020 ran 2 of 2 samples (0 unverified; 1 pointer-only for licence)
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network 1 1 17 Jan 2020 ran 1 of 11 samples (10 unverified)

The full list of 40 is in the JSON twin.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Stanford Online Products
  • SOP

2 variant names, as the archive lists them.

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