mlsanityData to 14 Oct 2026

1st Place Solution in Google Universal Images Embedding

arXiv 2210.08473 ↗First posted 16 Oct 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper presents the 1st place solution for the Google Universal Images Embedding Competition on Kaggle. The highlighted part of our solution is based on 1) A novel way to conduct training and fine-tuning; 2) The idea of a better ensemble in the pool of models that make embedding; 3) The potential trade-off between fine-tuning on high-resolution and overlapping patches; 4) The potential factors to work for the dynamic margin. Our solution reaches 0.728 in the private leader board, which achieve 1st place in Google Universal Images Embedding Competition.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 7 of its 14 references that are in the map. First posted on arXiv 16 Oct 2022.

Builds on

7 of 14 references.

References · 7

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  3. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  4. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  5. 2020Products-10K: A Large-scale Product Recognition Datasetcited by 42
  6. 2022The Met Dataset: Instance-level Recognition for Artworkscited by 40
  7. 2020Google Landmark Recognition 2020 Competition Third Place Solutioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 5; 2026: 1.

10 papers.

  1. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 129
  2. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 32
  3. 2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28
  4. 2024ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generationcited by 16
  5. 2025OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Modelscited by 9
  6. 20225th Place Solution to Kaggle Google Universal Image Embedding Competitioncited by 2
  7. 2024Efficient and Discriminative Image Feature Extraction for Universal Image Retrievalcited by 1
  8. 2025Single Image Iterative Subject-driven Generation and Editingcited by 0
  9. 2025MV-RAG: Retrieval Augmented Multiview Diffusioncited by 0
  10. 2026Alterbute: Editing Intrinsic Attributes of Objects in Imagescited by 0