# SEVEN: Deep Semi-supervised Verification Networks

## TL;DR

SEVEN is a deep semi-supervised verification network that effectively leverages both generative and discriminative components to improve verification accuracy in scenarios with scarce labeled data, outperforming state-of-the-art methods.

## Contribution

The paper introduces SEVEN, a novel end-to-end deep semi-supervised model combining generative and discriminative components for verification tasks with limited labeled data.

## Key findings

- SEVEN outperforms other semi-supervised techniques on four verification tasks.
- SEVEN is competitive with fully supervised models trained on more data.
- The generative component significantly enhances verification performance.

## Abstract

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.