vix.ing · top · new · best · stats · spec

Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks

2018/07/20 by Siddharth Roheda, Roheda, Siddharth, Benjamin S. Riggan +5 · 1 citation
Computer Science · Earth and Planetary Sciences · Engineering · #FOS: Electrical engineering #Geophysical Methods and Applications #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Underwater Acoustics Research #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1807.07682

openalex publication_date 2018/07/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose to use a Conditional Generative Adversarial Network (CGAN) for distilling (i.e. transferring) knowledge from sensor data and enhancing low-resolution target detection. In unconstrained surveillance settings, sensor measurements are often noisy, degraded, corrupted, and even missing/absent, thereby presenting a significant problem for multi-modal fusion. We therefore specifically tackle the problem of a missing modality in our attempt to propose an algorithm based on CGANs to generate representative information from the missing modalities when given some other available modalities. Despite modality gaps, we show that one can distill knowledge from one set of modalities to another. Moreover, we demonstrate that it achieves better performance than traditional approaches and recent teacher-student models.

Citations

Cited by

Related