Meta-Mining Discriminative Samples for Kinship Verification

03/28/2021
by   Wanhua Li, et al.
0

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.

READ FULL TEXT

page 4

page 5

research
02/10/2022

Energy-Based Contrastive Learning of Visual Representations

Contrastive learning is a method of learning visual representations by t...
research
12/16/2022

Hard Sample Aware Network for Contrastive Deep Graph Clustering

Contrastive deep graph clustering, which aims to divide nodes into disjo...
research
01/03/2023

Cluster-guided Contrastive Graph Clustering Network

Benefiting from the intrinsic supervision information exploitation capab...
research
02/07/2023

Towards Better Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach

Not all positive pairs are beneficial to time series contrastive learnin...
research
12/09/2021

HBReID: Harder Batch for Re-identification

Triplet loss is a widely adopted loss function in ReID task which pulls ...
research
12/06/2019

Visual-Textual Association with Hardest and Semi-Hard Negative Pairs Mining for Person Search

Searching persons in large-scale image databases with the query of natur...
research
09/14/2023

Kinship Verification from rPPG using 1DCNN Attention networks

Facial kinship verification aims at automatically determining whether tw...

Please sign up or login with your details

Forgot password? Click here to reset