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

arXiv: https://arxiv.org/abs/2104.02230 · HTML: https://mlsanity.com/paper/2104.02230/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 77 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 30 of 50)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)

## Built on by (most cited first, 12 of 12)

- [Edge-guided Representation Learning for Underwater Object Detection](https://mlsanity.com/paper/2306.00440/) (2023)
- [Domain Generalisation for Object Detection under Covariate and Concept Shift](https://mlsanity.com/paper/2203.05294/) (2022)
- [A Gated Cross-domain Collaborative Network for Underwater Object Detection](https://mlsanity.com/paper/2306.14141/) (2023)
- [UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection](https://mlsanity.com/paper/2309.04708/) (2023)
- [Context in object detection: a systematic literature review](https://mlsanity.com/paper/2503.23249/) (2025)
- [ADOD: Adaptive Domain-Aware Object Detection with Residual Attention for Underwater Environments](https://mlsanity.com/paper/2312.06801/) (2023)
- [U-DECN: End-to-End Underwater Object Detection ConvNet with Improved DeNoising Training](https://mlsanity.com/paper/2408.05780/) (2024)
- [Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection](https://mlsanity.com/paper/2401.05401/) (2023)
- [SynerMix: Synergistic Mixup Solution for Enhanced Intra-Class Cohesion and Inter-Class Separability in Image Classification](https://mlsanity.com/paper/2403.14137/) (2024)
- [Why Domain Matters: A Preliminary Study of Domain Effects in Underwater Object Detection](https://mlsanity.com/paper/2604.26174/) (2026)
- [Why Domain Matters: Domain-Aware Benchmarking of Underwater Object Detection and Annotation Quality](https://mlsanity.com/paper/2607.10575/) (2026)
- [Domain generalization and synthetic data in object detection: the enabler, the probe, and the gap](https://mlsanity.com/paper/2610.00030/) (2026)

## Abstract (arXiv)

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.