FIOD-VUE: Focusing on Invariant Information in Object Detection of Varying Underwater Environment
Zhuoran Xie, Miao Yang, Mengjiao Shen, Yuquan Qiu, Xinyu Wang
Abstract
The varying environmental conditions pose challenges to existing object detection methods as they lead to changes in the overall feature distribution of images. Underwater images are particularly susceptible to environmental conditions changes, resulting in phenomena like color deviation. This paper propose an object detection model, FIOD-VUE, which focuses on invariant information across different underwater environments to enhance the model’s generalization capability. Inspired by frequency domain analysing, we design a Frequency-Invariant Attention (FIA) module. This module use frequency filters to focus on specific frequency signals, i.e., cross-domain invariant information. Additionally, we design the Multi-scale Image-level Feature Alignment (MIFA) to adaptively adjust the frequency filters in the FIA and assist the backbone in extracting domain-confusion features. Through adversarial training, the distribution gap between the source domain and target domain is reduced. To enrich the domain shift database, we also afford an HD-Deepfish dataset. Numerous experiments on the S-UODAC2020 and the HD-Deepfish datasets were executed and yielded impressive results, with average precision (AP) scores of 56.8% and 37.1%, respectively, surpassing the performance of the existing underwater object detection (UOD) models. The link of the code is released at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/JOU-UIP/FIOD-VUE</uri>.