# Task-Driven Common Representation Learning via Bridge Neural Network

arXiv: https://arxiv.org/abs/1906.10897 · HTML: https://mlsanity.com/paper/1906.10897/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2019.

## Built on by (most cited first, 2 of 2)

- [The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion](https://mlsanity.com/paper/2103.08259/) (2021)
- [Boosting ship detection in SAR images with complementary pretraining techniques](https://mlsanity.com/paper/2103.08251/) (2021)

## Abstract (arXiv)

This paper introduces a novel deep learning based method, named bridge neural network (BNN) to dig the potential relationship between two given data sources task by task. The proposed approach employs two convolutional neural networks that project the two data sources into a feature space to learn the desired common representation required by the specific task. The training objective with artificial negative samples is introduced with the ability of mini-batch training and it's asymptotically equivalent to maximizing the total correlation of the two data sources, which is verified by the theoretical analysis. The experiments on the tasks, including pair matching, canonical correlation analysis, transfer learning, and reconstruction demonstrate the state-of-the-art performance of BNN, which may provide new insights into the aspect of common representation learning.