Use Classifier as Generator

2022/09/10 by Haoyang Li, Li, Haoyang
Biochemistry, Genetics and Molecular Biology · Engineering · Medicine · #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Retinal Imaging and Analysis

paper · pdf · doi:10.48550/arxiv.2209.09210

openalex publication_date 2022/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Image recognition/classification is a widely studied problem, but its reverse problem, image generation, has drawn much less attention until recently. But the vast majority of current methods for image generation require training/retraining a classifier and/or a generator with certain constraints, which can be hard to achieve. In this paper, we propose a simple approach to directly use a normally trained classifier to generate images. We evaluate our method on MNIST and show that it produces recognizable results for human eyes with limited quality with experiments.

Related

• Generator Born from Classifier
• Image Synthesis with a Single (Robust) Classifier
• Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs
• This dataset does not exist: training models from generated images
• The role of machine learning algorithms in image classification