# Meta-Mining Discriminative Samples for Kinship Verification

arXiv: https://arxiv.org/abs/2103.15108 · HTML: https://mlsanity.com/paper/2103.15108/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 59 references that are in the map.
- First posted on arXiv 28 Mar 2021.

## Builds on (most cited first, 24 of 24)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Suppressing Uncertainties for Large-Scale Facial Expression Recognition](https://mlsanity.com/paper/2002.10392/) (2020)
- [Learning Meta Face Recognition in Unseen Domains](https://mlsanity.com/paper/2003.07733/) (2020)
- [Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation](https://mlsanity.com/paper/1906.06196/) (2019)
- [BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation](https://mlsanity.com/paper/1904.03358/) (2019)
- [Domain Balancing: Face Recognition on Long-Tailed Domains](https://mlsanity.com/paper/2003.13791/) (2020)
- [Learning Social Relation Traits from Face Images](https://mlsanity.com/paper/1509.03936/) (2015)
- [Graph-Based Social Relation Reasoning](https://mlsanity.com/paper/2007.07453/) (2020)
- [Tri-Subject Kinship Verification: Understanding the Core of A Family](https://mlsanity.com/paper/1501.02555/) (2015)
- [Graph-based Kinship Reasoning Network](https://mlsanity.com/paper/2004.10375/) (2020)
- [Kinship Identification through Joint Learning Using Kinship Verification Ensembles](https://mlsanity.com/paper/2004.06382/) (2020)
- [Group Membership Prediction](https://mlsanity.com/paper/1509.04783/) (2015)
- [Hierarchical Representation Learning for Kinship Verification](https://mlsanity.com/paper/1805.10557/) (2018)

## Built on by (most cited first, 4 of 4)

- [MetaAge: Meta-Learning Personalized Age Estimators](https://mlsanity.com/paper/2207.05288/) (2022)
- [Kinship Representation Learning with Face Componential Relation](https://mlsanity.com/paper/2304.04546/) (2023)
- [ChildPredictor: A Child Face Prediction Framework with Disentangled Learning](https://mlsanity.com/paper/2204.09962/) (2022)
- [Kinship Verification through a Forest Neural Network](https://mlsanity.com/paper/2504.18910/) (2025)

## Abstract (arXiv)

Kinship verification aims to find out whether there is a kin relation for a given pair of facial images. Kinship verification databases are born with unbalanced data. For a database with N positive kinship pairs, we naturally obtain N(N-1) negative pairs. How to fully utilize the limited positive pairs and mine discriminative information from sufficient negative samples for kinship verification remains an open issue. To address this problem, we propose a Discriminative Sample Meta-Mining (DSMM) approach in this paper. Unlike existing methods that usually construct a balanced dataset with fixed negative pairs, we propose to utilize all possible pairs and automatically learn discriminative information from data. Specifically, we sample an unbalanced train batch and a balanced meta-train batch for each iteration. Then we learn a meta-miner with the meta-gradient on the balanced meta-train batch. In the end, the samples in the unbalanced train batch are re-weighted by the learned meta-miner to optimize the kinship models. Experimental results on the widely used KinFaceW-I, KinFaceW-II, TSKinFace, and Cornell Kinship datasets demonstrate the effectiveness of the proposed approach.