English

PlankFormer: Robust Plankton Instance Segmentation via MAE-Pretrained Vision Transformers and Pseudo Community Image Generation

Computer Vision and Pattern Recognition 2026-04-21 v1

Abstract

Plankton monitoring is essential for assessing aquatic ecosystems but is limited by the labor-intensive nature of manual microscopic analysis. Automating the segmentation of plankton from crowded images is crucial, however, it faces two major challenges: (i) the scarcity of pixel-level annotated datasets and (ii) the difficulty of distinguishing plankton from debris and overlapping individuals using conventional CNN-based methods. To address these issues, we propose PlankFormer, a novel framework for plankton instance segmentation. First, to overcome the data shortage, we introduce a method to generate labeled Pseudo Community Images (PCI) by synthesizing individual plankton images onto diverse backgrounds, including those created by generative models. Second, we propose a segmentation model utilizing a Vision Transformer (ViT) backbone with a Mask2Former decoder. To robustly capture the global structural features of plankton against occlusion and debris, we employ a Masked Autoencoder (MAE) for self-supervised pre-training on unlabeled individual images. Experimental results on real-world datasets demonstrate that our method significantly outperforms conventional methods, such as Mask R-CNN, particularly in challenging environments with high debris density. We demonstrate that our synthetic training strategy and MAE-based architecture enable high-precision segmentation with requiring less manual annotations for individual plankton images.

Keywords

Cite

@article{arxiv.2604.17856,
  title  = {PlankFormer: Robust Plankton Instance Segmentation via MAE-Pretrained Vision Transformers and Pseudo Community Image Generation},
  author = {Masaharu Miyazaki and Yurie Otake and Koichi Ito and Wataru Makino and Jotaro Urabe and Takafumi Aoki},
  journal= {arXiv preprint arXiv:2604.17856},
  year   = {2026}
}

Comments

Accepted to ICPR2026

R2 v1 2026-07-01T12:17:41.965Z