paper-with-me

Papers

Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples

2018-06-07 · Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre

This work addresses the scarcity of annotated hyperspectral data required to train deep neural networks. Especially, we investigate generative adversarial networks and their application to the synthesis of consistent labeled spectra. By training such networks on public datasets, we show that these models are not only able to capture the underlying distribution, but also to generate genuine-looking and physically plausible spectra. Moreover, we experimentally validate that the synthetic samples can be used as an effective data augmentation strategy. We validate our approach on several public hyper-spectral datasets using a variety of deep classifiers.

📄 PDF Abstract BibTeX arXiv:1806.02583

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis

2024-01-01 · CVPR 2024 1 · Yang Yu, Erting Pan, Xinya Wang, Yuheng Wu 외

In the realm of AI data serves as a pivotal resource. Real-world hyperspectral images (HSIs) bearing wide spectral characteristics are particularly valuable. However the acquisition of HSIs is always costly and time-…

Image Generation

Deep Diffusion Models and Unsupervised Hyperspectral Unmixing for Realistic Abundance Map Synthesis

2025-06-16 · Martina Pastorino, Michael Alibani, Nicola Acito, Gabriele Moser

This paper presents a novel methodology for generating realistic abundance maps from hyperspectral imagery using an unsupervised, deep-learning-driven approach. Our framework integrates blind linear hyperspectral unmixin…

BenchmarkingData AugmentationEarth ObservationHyperspectral Unmixing+1

Language-Informed Hyperspectral Image Synthesis for Imbalanced-Small Sample Classification via Semi-Supervised Conditional Diffusion Model

2025-02-27 · Yimin Zhu, Linlin Xu

Although data augmentation is an effective method to address the imbalanced-small sample data (ISSD) problem in hyperspectral image classification (HSIC), most methodologies extend features in the latent space. Few, howe…

Data AugmentationHyperspectral Image Classificationimage-classificationImage Classification+1

POLICY DRIVEN GENERATIVE ADVERSARIAL NETWORKS FOR ACCENTED SPEECH GENERATION

2018-01-01 · ICLR 2018 1 · Prannay Khosla, Preethi Jyothi, Vinay P. Namboodiri, Mukundhan Srinivasan

In this paper, we propose the generation of accented speech using generative adversarial networks. Through this work we make two main contributions a) The ability to condition latent representations while generating real…

Speech Synthesis

Conditional Image Synthesis With Auxiliary Classifier GANs

2016-10-30 · ICML 2017 8 · Augustus Odena, Christopher Olah, Jonathon Shlens

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for im…

Conditional Image GenerationDiversityImage GenerationImage Quality Assessment