# 2nd Place Solution to Google Universal Image Embedding

arXiv: https://arxiv.org/abs/2210.08735 · HTML: https://mlsanity.com/paper/2210.08735/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 17 Oct 2022.

## Builds on (most cited first, 6 of 6)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers](https://mlsanity.com/paper/2110.03786/) (2021)

## Built on by (most cited first, 2 of 2)

- [Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations](https://mlsanity.com/paper/2309.01858/) (2023)
- [Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval](https://mlsanity.com/paper/2409.13513/) (2024)

## Abstract (arXiv)

Image representations are a critical building block of computer vision applications. This paper presents the 2nd place solution to the Google Universal Image Embedding Competition, which is part of the ECCV2022 instance-level recognition workshops. We use the instance-level fine-grained image classification method to complete this competition. We focus on data building and processing, model structure, and training strategies. Finally, the solution scored 0.713 on the public leaderboard and 0.709 on the private leaderboard.