Reduced Focal Loss: 1st Place Solution to xView object detection in Satellite Imagery

Abstract

This paper describes our approach to the DIUx xView 2018 Detection Challenge [1]. This challenge focuses on a new satellite imagery dataset. The dataset contains 60 object classes that are highly imbalanced. Due to the imbalanced nature of the dataset, the training process becomes significantly more challenging. To address this problem, we introduce a novel Reduced Focal Loss function, which brought us 1st place in the DIUx xView 2018 Detection Challenge.

Cited by in corpus (4)

• Detection of masses and architectural distortions in digital breast tomosynthesis: a publicly available dataset of 5,060 patients and a deep learning model
• Oriented Bounding Boxes for Small and Freely Rotated Objects
• Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance
• Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery