Reducing the need for bounding box annotations in Object Detection using Image Classification data

Author(s)

Blanger, Leonardo ; Hirata, Nina S. T. ; Jiang, Xiaoyi ; IEEE Comp Soc

• Document type: Journal article
• Source: 2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021); v. N/A, p. 8-pg., 2021-01-01.

Abstract

We address the problem of training Object Detection models using significantly less bounding box annotated images. For that, we take advantage of cheaper and more abundant image classification data. Our proposal consists in automatically generating artificial detection samples, with no need of expensive detection level supervision, using images with classification labels only. We also detail a pretraining initialization strategy for detection architectures using these artificially synthesized samples, before finetuning on real detection data, and experimentally show how this consistently leads to more data efficient models. With the proposed approach, we were able to effectively use only classification data to improve results on the harder and more supervision hungry object detection problem. We achieve results equivalent to those of the full data scenario using only a small fraction of the original detection data for Face, Bird, and Car detection. (AU)

• FAPESP's process: 18/00390-7 - QR code detection using deep learning models
• Grantee: Leonardo Blanger
• Support Opportunities: Scholarships in Brazil - Master
• FAPESP's process: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery
• Grantee: Roberto Marcondes Cesar Junior
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 17/25835-9 - Understanding images and deep learning models
• Grantee: Nina Sumiko Tomita Hirata
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• FAPESP's process: 19/17312-1 - Adversarial learning of image augmentation policies for object detection
• Grantee: Leonardo Blanger
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree