Adversarial learning of image augmentation policies for object detection

• Grant number: 19/17312-1
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date until: October 01, 2019
• End date until: March 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Nina Sumiko Tomita Hirata
• Grantee: Leonardo Blanger
• Supervisor: Xiaoyi Jiang
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Institution abroad: University of Munster, Germany
• Associated to the scholarship: 18/00390-7 - QR code detection using deep learning models, BP.MS

Abstract

Recent deep learning architectures have achieved impressive results on the task of Object Detection. However, such techniques are known to require huge amounts of labeled data in order to properly generalize, which is harder to acquire than traditional image classification data. To improve this situation, the use of image augmentation techniques became standard practice on the literature. This traditional forms of augmentation consist mostly of fixed sequences of handcrafted image operations with random parameters, which already helps counteract the lack of labeled data on generic object detection, although not being enough in more specific, low data scenarios. In this perspective, a few works already apply image generation techniques to artificially create novel training samples, but to the best of our knowledge, none of them addresses object detection yet.Parallel to this, recently proposed generative models, based on the GAN framework, have achieved impressive results in terms of image realism for some classes of objects, and works on image augmentation already employ them for classification tasks.The goal of the proposed internship is to investigate the application of recently proposed generative adversarial architectures for the automatic generation of labeled samples, in a way that improves the performance of deep learning based object detection models. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BLANGER, LEONARDO; HIRATA, NINA S. T.; JIANG, XIAOYI; IEEE COMP SOC. Reducing the need for bounding box annotations in Object Detection using Image Classification data. 2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021), v. N/A, p. 8-pg., 2021-01-01. (18/00390-7, 15/22308-2, 17/25835-9, 19/17312-1)