Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning

TL;DR

This paper introduces a novel domain generalization framework for underwater object detection that combines style transfer, feature-level mixup, and contrastive learning to improve robustness across diverse underwater environments.

Contribution

It proposes a new framework (DMC) that leverages style transfer, feature mixup, and contrastive loss to enhance domain invariance and detection performance in underwater environments.

Findings

Outperforms existing domain generalization methods on S-UODAC2020, PACS, and VLCS datasets.

Enables detectors to be robust against domain shifts in underwater environments.

Establishes a new benchmark S-UODAC2020 for evaluating underwater object detection generalization.

Abstract

The performance of existing underwater object detection methods degrades seriously when facing domain shift caused by complicated underwater environments. Due to the limitation of the number of domains in the dataset, deep detectors easily memorize a few seen domains, which leads to low generalization ability. There are two common ideas to improve the domain generalization performance. First, it can be inferred that the detector trained on as many domains as possible is domain-invariant. Second, for the images with the same semantic content in different domains, their hidden features should be equivalent. This paper further excavates these two ideas and proposes a domain generalization framework (named DMC) that learns how to generalize across domains from Domain Mixup and Contrastive Learning. First, based on the formation of underwater images, an image in an underwater environment is the linear transformation of another underwater environment. Thus, a style transfer model, which outputs a linear transformation matrix instead of the whole image, is proposed to transform images from one source domain to another, enriching the domain diversity of the training data. Second, mixup operation interpolates different domains on the feature level, sampling new domains on the domain manifold. Third, contrastive loss is selectively applied to features from different domains to force the model to learn domain invariant features but retain the discriminative capacity. With our method, detectors will be robust to domain shift. Also, a domain generalization benchmark S-UODAC2020 for detection is set up to measure the performance of our method. Comprehensive experiments on S-UODAC2020 and two object recognition benchmarks (PACS and VLCS) demonstrate that the proposed method is able to learn domain-invariant representations, and outperforms other domain generalization methods.