# Orthonormal Product Quantization Network for Scalable Face Image Retrieval

arXiv: https://arxiv.org/abs/2107.00327 · HTML: https://mlsanity.com/paper/2107.00327/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 59 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Deep Supervised Discrete Hashing](https://mlsanity.com/paper/1705.10999/) (2017)
- [Deep Supervised Hashing with Triplet Labels](https://mlsanity.com/paper/1612.03900/) (2016)
- [Generalized Product Quantization Network for Semi-supervised Image Retrieval](https://mlsanity.com/paper/2002.11281/) (2020)
- [End-to-End Supervised Product Quantization for Image Search and Retrieval](https://mlsanity.com/paper/1711.08589/) (2017)
- [Deep Triplet Quantization](https://mlsanity.com/paper/1902.00153/) (2019)
- [Fast Supervised Discrete Hashing](https://mlsanity.com/paper/1904.03556/) (2019)
- [How should we evaluate supervised hashing?](https://mlsanity.com/paper/1609.06753/) (2016)
- [Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss](https://mlsanity.com/paper/1803.04137/) (2018)
- [Supervised Quantization for Similarity Search](https://mlsanity.com/paper/1902.00617/) (2019)
- [Deep Momentum Uncertainty Hashing](https://mlsanity.com/paper/2009.08012/) (2020)
- [Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval](https://mlsanity.com/paper/2103.09442/) (2021)

## Built on by (most cited first, 1 of 1)

- [15M Multimodal Facial Image-Text Dataset](https://mlsanity.com/paper/2407.08515/) (2024)

## Abstract (arXiv)

Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations like pose, illumination, and expressions in face images, still pose a challenge for face image retrieval. In light of this, face image retrieval requires sufficiently powerful learning metrics, which are absent in current deep quantization works. Moreover, to tackle the growing unseen identities in the query stage, face image retrieval drives more demands regarding model generalization and system scalability than general image retrieval tasks. This paper integrates product quantization with orthonormal constraints into an end-to-end deep learning framework to effectively retrieve face images. Specifically, a novel scheme that uses predefined orthonormal vectors as codewords is proposed to enhance the quantization informativeness and reduce codewords' redundancy. A tailored loss function maximizes discriminability among identities in each quantization subspace for both the quantized and original features. An entropy-based regularization term is imposed to reduce the quantization error. Experiments are conducted on four commonly-used face datasets under both seen and unseen identities retrieval settings. Our method outperforms all the compared deep hashing/quantization state-of-the-arts under both settings. Results validate the effectiveness of the proposed orthonormal codewords in improving models' standard retrieval performance and generalization ability. Combing with further experiments on two general image datasets, it demonstrates the broad superiority of our method for scalable image retrieval.