# Producing augmentation-invariant embeddings from real-life imagery

arXiv: https://arxiv.org/abs/2112.03415 · HTML: https://mlsanity.com/paper/2112.03415/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 5 of 5)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [The 2021 Image Similarity Dataset and Challenge](https://mlsanity.com/paper/2106.09672/) (2021)

## Built on by (most cited first, 6 of 6)

- [Results and findings of the 2021 Image Similarity Challenge](https://mlsanity.com/paper/2202.04007/) (2022)
- [A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection](https://mlsanity.com/paper/2205.12358/) (2022)
- [AnyPattern: Towards In-context Image Copy Detection](https://mlsanity.com/paper/2404.13788/) (2024)
- [Image Copy Detection for Diffusion Models](https://mlsanity.com/paper/2409.19952/) (2024)
- [Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection](https://mlsanity.com/paper/2405.17928/) (2024)
- [Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection](https://mlsanity.com/paper/2602.17484/) (2026)

## Abstract (arXiv)

This article presents an efficient way to produce feature-rich, high-dimensionality embedding spaces from real-life images. The features produced are designed to be independent from augmentations used in real-life cases which appear on social media. Our approach uses convolutional neural networks (CNN) to produce an embedding space. An ArcFace head was used to train the model by employing automatically produced augmentations. Additionally, we present a way to make an ensemble out of different embeddings containing the same semantic information, a way to normalize the resulting embedding using an external dataset, and a novel way to perform quick training of these models with a high number of classes in the ArcFace head. Using this approach we achieved the 2nd place in the 2021 Facebook AI Image Similarity Challenge: Descriptor Track.