A full data augmentation pipeline for small object detection based on generative adversarial networks. (January 2023)

• Record Type: Journal Article
• Authors: Bosquet, Brais; Cores, Daniel; Seidenari, Lorenzo; Brea, Víctor M.; Mucientes, Manuel; Bimbo, Alberto Del
• Is Part Of: Pattern recognition. Volume 133(2023)
• Publication Date: 2023-01
• Subjects: Small object detection -- Data augmentation -- Generative adversarial network; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108998
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Full pipeline for data augmentation for small object detection. High-quality synthetic data combining a GAN with image inpainting and blending. DS-GAN generates realistic small objects from larger ones. Abstract: Object detection accuracy on small objects, i.e., objects under 32 × 32 pixels, lags behind that of large ones. To address this issue, innovative architectures have been designed and new datasets have been released. Still, the number of small objects in many datasets does not suffice for training. The advent of the generative adversarial networks (GANs) opens up a new data augmentation possibility for training architectures without the costly task of annotating huge datasets for small objects. In this paper, we propose a full pipeline for data augmentation for small object detection which combines a GAN-based object generator with techniques of object segmentation, image inpainting, and image blending to achieve high-quality synthetic data. The main component of our pipeline is DS-GAN, a novel GAN-based architecture that generates realistic small objects from larger ones. Experimental results show that our overall data augmentation method improves the performance of state-of-the-art models up to 11.9% AP s @ . 5 on UAVDT and by 4.7% AP s @ . 5 on iSAID, both for the small objects subset and for a scenario where the number of training instances is limited.