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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miyazaki, Masaharu, Otake, Yurie, Ito, Koichi, Makino, Wataru, Urabe, Jotaro, Aoki, Takafumi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908978676498432
author Miyazaki, Masaharu
Otake, Yurie
Ito, Koichi
Makino, Wataru
Urabe, Jotaro
Aoki, Takafumi
author_facet Miyazaki, Masaharu
Otake, Yurie
Ito, Koichi
Makino, Wataru
Urabe, Jotaro
Aoki, Takafumi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17856
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PlankFormer: Robust Plankton Instance Segmentation via MAE-Pretrained Vision Transformers and Pseudo Community Image Generation
Miyazaki, Masaharu
Otake, Yurie
Ito, Koichi
Makino, Wataru
Urabe, Jotaro
Aoki, Takafumi
Computer Vision and Pattern Recognition
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.
title PlankFormer: Robust Plankton Instance Segmentation via MAE-Pretrained Vision Transformers and Pseudo Community Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.17856