# Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers

arXiv: https://arxiv.org/abs/2110.03786 · HTML: https://mlsanity.com/paper/2110.03786/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features](https://mlsanity.com/paper/2108.02927/) (2021)
- [Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset](https://mlsanity.com/paper/1906.04087/) (2019)
- [Unifying Deep Local and Global Features for Image Search](https://mlsanity.com/paper/2001.05027/) (2020)
- [Supporting large-scale image recognition with out-of-domain samples](https://mlsanity.com/paper/2010.01650/) (2020)
- [Google Landmark Recognition 2020 Competition Third Place Solution](https://mlsanity.com/paper/2010.05350/) (2020)
- [Towards A Fairer Landmark Recognition Dataset](https://mlsanity.com/paper/2108.08874/) (2021)

## Built on by (most cited first, 3 of 3)

- [2nd Place Solution to Google Universal Image Embedding](https://mlsanity.com/paper/2210.08735/) (2022)
- [Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification](https://mlsanity.com/paper/2304.07883/) (2023)
- [Google Landmark Retrieval 2021 Competition Third Place Solution](https://mlsanity.com/paper/2110.04619/) (2021)

## Abstract (arXiv)

We present an efficient end-to-end pipeline for largescale landmark recognition and retrieval. We show how to combine and enhance concepts from recent research in image retrieval and introduce two architectures especially suited for large-scale landmark identification. A model with deep orthogonal fusion of local and global features (DOLG) using an EfficientNet backbone as well as a novel Hybrid-Swin-Transformer is discussed and details how to train both architectures efficiently using a step-wise approach and a sub-center arcface loss with dynamic margins are provided. Furthermore, we elaborate a novel discriminative re-ranking methodology for image retrieval. The superiority of our approach was demonstrated by winning the recognition and retrieval track of the Google Landmark Competition 2021.