Skip to main navigation Skip to search Skip to main content

Towards ancient plant seed classification: a benchmark dataset and baseline model

  • Rui XING
  • , Runmin CONG*
  • , Yingying WU
  • , Can WANG*
  • , Zhongming TANG
  • , Fen WANG
  • , Hao WU
  • , Sam KWONG
  • *Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

Abstract

Understanding dietary preferences in ancient societies is essential for revealing human–environment interactions. Seeds are key archaeological artifacts in archaeobotanical research, yet their identification still relies on expert knowledge, making large-scale analysis inefficient. Although analytical methods in archaeology have advanced, data and methodological gaps persist, particularly in the classification of ancient plant seeds. To address this issue, we construct the first Ancient Plant Seed Image Classification (APS) dataset, containing 8340 images from 17 genus- or species-level categories excavated from 18 archaeological sites across China. We further propose APSNet, a classification framework for ancient plant seeds. APSNet introduces seed scale information via a Size Perception and Embedding (SPE) module to complement fine-grained features, and employs an Asynchronous Decoupled Decoding (ADD) architecture to learn discriminative features from channel and spatial perspectives. Experiments show APSNet outperforms state-of-the-art methods, achieving 90.2% accuracy and providing an effective tool for archaeological research.
Original languageEnglish
Article number538
Number of pages15
Journalnpj Heritage Science
Volume14
Issue number1
Early online date22 Jun 2026
DOIs
Publication statusE-pub ahead of print - 22 Jun 2026

Bibliographical note

Publisher Copyright:
© The Author(s) 2026.

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62471278; in part by the National Cultural Heritage Administration through the Key Scientific Research Base of Paleoenvironment Reconstruction and Subsistence Studies in Archaeology (Shandong University) under Grant SDULA202504; in part by the National Cultural Heritage Administration under Grant 2025-332; in part by the Archaeological Talent Promotion Program of China under Grant 2024-270; in part by the Hong Kong GRF–RGC General Research Fund under Grant 13200425; and in part by the Research Grants Council of the Hong Kong Special Administrative Region, China, under Grant STG5/E-103/24-R.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 11 - Sustainable Cities and Communities
    SDG 11 Sustainable Cities and Communities

Fingerprint

Dive into the research topics of 'Towards ancient plant seed classification: a benchmark dataset and baseline model'. Together they form a unique fingerprint.

Cite this