# 1st Place Solution in Google Universal Images Embedding

arXiv: https://arxiv.org/abs/2210.08473 · HTML: https://mlsanity.com/paper/2210.08473/

## 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 (most cited first, 7 of 7)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [Products-10K: A Large-scale Product Recognition Dataset](https://mlsanity.com/paper/2008.10545/) (2020)
- [The Met Dataset: Instance-level Recognition for Artworks](https://mlsanity.com/paper/2202.01747/) (2022)
- [Google Landmark Recognition 2020 Competition Third Place Solution](https://mlsanity.com/paper/2010.05350/) (2020)

## Built on by (most cited first, 10 of 10)

- [Phantom: Subject-consistent video generation via cross-modal alignment](https://mlsanity.com/paper/2502.11079/) (2025)
- [Does FLUX Already Know How to Perform Physically Plausible Image Composition?](https://mlsanity.com/paper/2509.21278/) (2025)
- [Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations](https://mlsanity.com/paper/2309.01858/) (2023)
- [ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation](https://mlsanity.com/paper/2412.08645/) (2024)
- [OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models](https://mlsanity.com/paper/2509.17627/) (2025)
- [5th Place Solution to Kaggle Google Universal Image Embedding Competition](https://mlsanity.com/paper/2210.09495/) (2022)
- [Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval](https://mlsanity.com/paper/2409.13513/) (2024)
- [Single Image Iterative Subject-driven Generation and Editing](https://mlsanity.com/paper/2503.16025/) (2025)
- [MV-RAG: Retrieval Augmented Multiview Diffusion](https://mlsanity.com/paper/2508.16577/) (2025)
- [Alterbute: Editing Intrinsic Attributes of Objects in Images](https://mlsanity.com/paper/2601.10714/) (2026)

## 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.