# Results and findings of the 2021 Image Similarity Challenge

arXiv: https://arxiv.org/abs/2202.04007 · HTML: https://mlsanity.com/paper/2202.04007/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Efficient Self-supervised Vision Transformers for Representation Learning](https://mlsanity.com/paper/2106.09785/) (2021)
- [Cross-Batch Memory for Embedding Learning](https://mlsanity.com/paper/1912.06798/) (2019)
- [The DeepFake Detection Challenge (DFDC) Dataset](https://mlsanity.com/paper/2006.07397/) (2020)
- [The 2021 Image Similarity Dataset and Challenge](https://mlsanity.com/paper/2106.09672/) (2021)
- [AugLy: Data Augmentations for Robustness](https://mlsanity.com/paper/2201.06494/) (2022)
- [Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection](https://mlsanity.com/paper/2112.04323/) (2021)
- [Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond](https://mlsanity.com/paper/2006.06525/) (2020)
- [Bag of Tricks and A Strong baseline for Image Copy Detection](https://mlsanity.com/paper/2111.08004/) (2021)
- [D2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection](https://mlsanity.com/paper/2111.07090/) (2021)
- [Producing augmentation-invariant embeddings from real-life imagery](https://mlsanity.com/paper/2112.03415/) (2021)
- [3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity Challenge](https://mlsanity.com/paper/2112.02373/) (2021)
- [2nd Place Solution to Facebook AI Image Similarity Challenge Matching Track](https://mlsanity.com/paper/2111.09113/) (2021)

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

- [VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2403.06098/) (2024)
- [TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision](https://mlsanity.com/paper/2211.13090/) (2022)
- [TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation](https://mlsanity.com/paper/2411.04709/) (2024)
- [Active Image Indexing](https://mlsanity.com/paper/2210.10620/) (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)
- [General Image Descriptors for Open World Image Retrieval using ViT CLIP](https://mlsanity.com/paper/2210.11141/) (2022)
- [3rd Place Solution to Meta AI Video Similarity Challenge](https://mlsanity.com/paper/2304.11964/) (2023)
- [Origin Identification for Text-Guided Image-to-Image Diffusion Models](https://mlsanity.com/paper/2501.02376/) (2025)
- [Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection](https://mlsanity.com/paper/2602.17484/) (2026)

## Abstract (arXiv)

The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods. There were 200 participants to the competition. This paper presents a quantitative and qualitative analysis of the top submissions. It appears that the most difficult image transformations involve either severe image crops or hiding into unrelated images, combined with local pixel perturbations. The key algorithmic elements in the winning submissions are: training on strong augmentations, self-supervised learning, score normalization, explicit overlay detection, and global descriptor matching followed by pairwise image comparison.