GUNNEL: Guided Mixup Augmentation and Multi-Model Fusion for Aquatic Animal Segmentation

TL;DR

This paper introduces GUNNEL, a novel framework combining guided mixup augmentation and multi-model fusion to enhance aquatic animal segmentation, supported by a new challenging dataset and extensive experiments showing superior performance.

Contribution

The paper presents a new aquatic animal dataset and a novel GUNNEL framework that improves segmentation accuracy through innovative data augmentation and model fusion techniques.

Findings

GUNNEL outperforms existing state-of-the-art methods.

The new dataset challenges current segmentation models.

Extensive experiments validate the effectiveness of GUNNEL.

Abstract

Recent years have witnessed great advances in object segmentation research. In addition to generic objects, aquatic animals have attracted research attention. Deep learning-based methods are widely used for aquatic animal segmentation and have achieved promising performance. However, there is a lack of challenging datasets for benchmarking. In this work, we build a new dataset dubbed "Aquatic Animal Species." We also devise a novel GUided mixup augmeNtatioN and multi-modEl fusion for aquatic animaL segmentation (GUNNEL) that leverages the advantages of multiple segmentation models to segment aquatic animals effectively and improves the training performance by synthesizing hard samples. Extensive experiments demonstrated the superiority of our proposed framework over existing state-of-the-art instance segmentation methods. The code is available at https://github.com/lmquan2000/mask-mixup. The dataset is available at https://doi.org/10.5281/zenodo.8208877.