# Comparator Networks

arXiv: https://arxiv.org/abs/1807.11440 · HTML: https://mlsanity.com/paper/1807.11440/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2018.

## Built on by (most cited first, 13 of 13)

- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [Part-based Face Recognition with Vision Transformers](https://mlsanity.com/paper/2212.00057/) (2022)
- [LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition](https://mlsanity.com/paper/2403.08161/) (2024)
- [CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition](https://mlsanity.com/paper/2409.18876/) (2024)
- [Harnessing Unrecognizable Faces for Improving Face Recognition](https://mlsanity.com/paper/2106.04112/) (2021)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [Weakly Supervised Keypoint Discovery](https://mlsanity.com/paper/2109.13423/) (2021)
- [NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition](https://mlsanity.com/paper/2103.03503/) (2021)
- [Attention-based Partial Face Recognition](https://mlsanity.com/paper/2106.06415/) (2021)
- [MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance](https://mlsanity.com/paper/2101.09899/) (2021)
- [Face-NMS: A Core-set Selection Approach for Efficient Face Recognition](https://mlsanity.com/paper/2109.04698/) (2021)
- [On the Burstiness of Faces in Set](https://mlsanity.com/paper/2506.20312/) (2025)

## Abstract (arXiv)

The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not. The traditional approach to this problem is to learn to generate a feature vector per image, aggregate them into one vector to represent the set, and then compute the cosine similarity between sets. Instead, we design a neural network architecture that can directly learn set-wise verification. Our contributions are: (i) We propose a Deep Comparator Network (DCN) that can ingest a pair of sets (each may contain a variable number of images) as inputs, and compute a similarity between the pair--this involves attending to multiple discriminative local regions (landmarks), and comparing local descriptors between pairs of faces; (ii) To encourage high-quality representations for each set, internal competition is introduced for recalibration based on the landmark score; (iii) Inspired by image retrieval, a novel hard sample mining regime is proposed to control the sampling process, such that the DCN is complementary to the standard image classification models. Evaluations on the IARPA Janus face recognition benchmarks show that the comparator networks outperform the previous state-of-the-art results by a large margin.