SEVEN: Deep Semi-supervised Verification Networks

by   Vahid Noroozi, et al.
Lehigh University
Northwestern University
University of Illinois at Chicago

Verification determines whether two samples belong to the same class or not, and has important applications such as face and fingerprint verification, where thousands or millions of categories are present but each category has scarce labeled examples, presenting two major challenges for existing deep learning models. We propose a deep semi-supervised model named SEmi-supervised VErification Network (SEVEN) to address these challenges. The model consists of two complementary components. The generative component addresses the lack of supervision within each category by learning general salient structures from a large amount of data across categories. The discriminative component exploits the learned general features to mitigate the lack of supervision within categories, and also directs the generative component to find more informative structures of the whole data manifold. The two components are tied together in SEVEN to allow an end-to-end training of the two components. Extensive experiments on four verification tasks demonstrate that SEVEN significantly outperforms other state-of-the-art deep semi-supervised techniques when labeled data are in short supply. Furthermore, SEVEN is competitive with fully supervised baselines trained with a larger amount of labeled data. It indicates the importance of the generative component in SEVEN.


page 1

page 2

page 3

page 4


Partly Supervised Multitask Learning

Semi-supervised learning has recently been attracting attention as an al...

Learning by Association - A versatile semi-supervised training method for neural networks

In many real-world scenarios, labeled data for a specific machine learni...

MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels

Supervised learning techniques are at the center of many tasks in remote...

Semi-supervised Learning using Adversarial Training with Good and Bad Samples

In this work, we investigate semi-supervised learning (SSL) for image cl...

Bayesian Semisupervised Learning with Deep Generative Models

Neural network based generative models with discriminative components ar...

Towards Semi-supervised Universal Graph Classification

Graph neural networks have pushed state-of-the-arts in graph classificat...

Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods

Small data challenges have emerged in many learning problems, since the ...

Please sign up or login with your details

Forgot password? Click here to reset