# GhostVLAD for set-based face recognition

arXiv: https://arxiv.org/abs/1810.09951 · HTML: https://mlsanity.com/paper/1810.09951/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2018.

## Built on by (most cited first, 17 of 17)

- [T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval](https://mlsanity.com/paper/2104.10054/) (2021)
- [Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection](https://mlsanity.com/paper/2207.10948/) (2022)
- [A Multi-View Approach To Audio-Visual Speaker Verification](https://mlsanity.com/paper/2102.06291/) (2021)
- [Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association](https://mlsanity.com/paper/2103.07293/) (2021)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [Deep Learning for Video-Text Retrieval: a Review](https://mlsanity.com/paper/2302.12552/) (2023)
- [A Bag-of-Prototypes Representation for Dataset-Level Applications](https://mlsanity.com/paper/2303.13251/) (2023)
- [VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation](https://mlsanity.com/paper/2202.10301/) (2022)
- [CoNAN: Conditional Neural Aggregation Network For Unconstrained Face Feature Fusion](https://mlsanity.com/paper/2307.10237/) (2023)
- [VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2409.19293/) (2024)
- [Audio-video fusion strategies for active speaker detection in meetings](https://mlsanity.com/paper/2206.10411/) (2022)
- [DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction](https://mlsanity.com/paper/2508.21407/) (2025)
- [AggNet: Learning to Aggregate Faces for Group Membership Verification](https://mlsanity.com/paper/2206.08683/) (2022)
- [Who is Authentic Speaker](https://mlsanity.com/paper/2405.00248/) (2024)
- [On the Burstiness of Faces in Set](https://mlsanity.com/paper/2506.20312/) (2025)
- [DCSCR: A Class-Specific Collaborative Representation based Network for Image Set Classification](https://mlsanity.com/paper/2508.12745/) (2025)
- [Video-Based Palm-Vein Authentication under Challenging Conditions](https://mlsanity.com/paper/2609.02776/) (2026)

## Abstract (arXiv)

The objective of this paper is to learn a compact representation of image sets for template-based face recognition. We make the following contributions: first, we propose a network architecture which aggregates and embeds the face descriptors produced by deep convolutional neural networks into a compact fixed-length representation. This compact representation requires minimal memory storage and enables efficient similarity computation. Second, we propose a novel GhostVLAD layer that includes em ghost clusters, that do not contribute to the aggregation. We show that a quality weighting on the input faces emerges automatically such that informative images contribute more than those with low quality, and that the ghost clusters enhance the network's ability to deal with poor quality images. Third, we explore how input feature dimension, number of clusters and different training techniques affect the recognition performance. Given this analysis, we train a network that far exceeds the state-of-the-art on the IJB-B face recognition dataset. This is currently one of the most challenging public benchmarks, and we surpass the state-of-the-art on both the identification and verification protocols.