Million-scale multimodal pollen microscopy with expert-guided foundation models

• URL: http://arxiv.org/abs/2606.17809v1
• Date: Tue, 16 Jun 2026 11:35:27 GMT
• Title: Million-scale multimodal pollen microscopy with expert-guided foundation models
• Abstract summary: Pollen AI Atlas is a million-scale multimodal pollen microscopy resource assembled from pure-slide bright-field images.<n>1,511,390 released grain detections with 99.6% proposal precision in expert-curated test regions.<n>Gemma4 provided the most controlled primary caption set, combining tight length control, no leakage and the strongest text-retrieval performance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated pollen identification from microscopy remains a bottleneck in aerobiology, palaeoecology and biodiversity monitoring, because scalable systems must generalise across specimen preparation, scanner settings and geographic origins while retaining palynological interpretability. To address this gap, we present a million-scale multimodal pollen microscopy resource, Pollen AI Atlas, assembled from pure-species whole-slide bright-field images spanning four geographic origins, four scanner settings and 46 taxon labels across 31 botanical families. Seeded by one manually selected exemplar per source slide, token-level mining and filtering produced 1,511,390 released grain detections with 99.6\% proposal precision in expert-curated test regions. Each detection was paired with machine-generated grain-level morphological captions from five open-weight vision-language models, guided by expert-verified palynological anchors, yielding structured descriptions of aperture systems, wall ornamentation, shape and size. Among the evaluated models, Gemma4 provided the most controlled primary caption set, combining tight length control, no leakage and the strongest text-retrieval performance. Baseline benchmarks with frozen visual features reached 88.16\% top-1 accuracy, while cross-regional retrieval showed that caption-derived text embeddings remained robust when image similarity degraded (mAP@20 0.811 versus 0.262). Released data, annotations, captions, splits, code, and weights provide a benchmark for pollen recognition, cross-regional domain adaptation and domain-specific multimodal microscopy learning.

Related papers

• Automated pipeline for herbarium label digitization [2.3991879782778853]
  HERBIOME is an end-to-end pipeline for automated herbarium label digitization.<n>It integrates YOLOv8-based component detection, CRAFT Hezar word-level text localization, fine-tuned TrOCR for recognition of handwritten and printed text, and GPT-4o Mini for semantic metadata structuring into standardized fields.
  arXiv  Detail & Related papers  (2026-08-25T14:01:32Z)
• A report-grounded vision-language foundation model for colonoscopy from 280000 routine reports [58.14965296904734]
  EndoCLIP is a vision-language foundation model trained on 125,756 lesion-level image-text pairs.<n>It outperforms general-purpose and biomedical vision-language encoders in both zero-shot and linear-probe settings.
  arXiv  Detail & Related papers  (2026-07-30T16:24:36Z)
• A Modelling and Evaluation Framework for EuroCrops-Driven Sentinel-2 Crop Segmentation [78.66324246922831]
  This work presents a pipeline for generating semantic-segmentation-ready agricultural datasets from Sentinel-2 imagery and EuroCrops parcel-level annotations.<n>The dataset contains 67,337 patches from five European countries and uses a reduced taxonomy of ten crop classes plus background.<n>A four-level U-Net with Group Normalization was trained using 10 Sentinel-2 spectral bands and a composite loss combining class-weighted cross-entropy and Dice loss.
  arXiv  Detail & Related papers  (2026-05-30T11:20:29Z)
• AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification [45.52399819498234]
  This work presents a systematic empirical comparison of three model paradigms for fine-grained crop disease classification.<n>We introduce AgriPath-LF16, a benchmark containing 111k images spanning 16 crops and 41 diseases.<n>CNNs achieve the highest accuracy on lab imagery but degrade under domain shift.<n> Contrastive VLMs provide a robust and parameter-efficient alternative with competitive cross-domain performance.
  arXiv  Detail & Related papers  (2026-03-08T17:28:01Z)
• OPTED: Open Preprocessed Trachoma Eye Dataset Using Zero-Shot SAM 3 Segmentation [0.0]
  Trachoma remains the leading infectious cause of blindness worldwide, with Sub-Saharan Africa bearing over 85% of the global burden and Ethiopia alone accounting for more than half of all cases.<n>Yet publicly available preprocessed datasets for automated trachoma classification are scarce, and none originate from the most affected region.<n>We present OPTED, an open-source preprocessed trachoma eye dataset constructed using the Segment Anything Model 3 (SAM 3) for automated region-of-interest extraction.
  arXiv  Detail & Related papers  (2026-03-06T21:07:08Z)
• Adaptive Multi-Scale Integration Unlocks Robust Cell Annotation in Histopathology Images [3.504506659662406]
  We build a marker-guided dataset from Xenium spatial transcriptomics with single-cell resolution labels for more than two million cells across eight organs.<n>We introduce NuClass, a pathologist workflow inspired framework for cell-wise multi-scale integration of nuclear morphology and microenvironmental context.<n>Our results demonstrate that multi-scale, uncertainty-aware fusion can bridge the gap between slide-level pathological foundation models and reliable, cell-level phenotype prediction.
  arXiv  Detail & Related papers  (2025-11-17T16:49:59Z)
• Overview of PlantCLEF 2024: multi-species plant identification in vegetation plot images [2.7110107174608173]
  The PlantCLEF 2024 challenge leverages a new test set of thousands of multi-label images annotated by experts and covering over 800 species.<n>It provides a large training set of 1.7 million individual plant images as well as state-of-the-art vision transformer models pre-trained on this data.<n>The aim is to predict all the plant species present on a high-resolution plot image.
  arXiv  Detail & Related papers  (2025-09-19T08:51:41Z)
• BeetleVerse: A Study on Taxonomic Classification of Ground Beetles [0.310688583550805]
  Ground beetles are a highly sensitive and speciose biological indicator, making them vital for monitoring biodiversity.<n>In this paper, we evaluate 12 vision models on taxonomic classification across four diverse, long-tailed datasets.<n>Our results show that the Vision and Language Transformer combined with an head is the best performing model, with 97% accuracy at genus and species level.
  arXiv  Detail & Related papers  (2025-04-18T01:06:37Z)
• SpectralEarth: Training Hyperspectral Foundation Models at Scale [47.93167977587301]
  We introduce SpectralEarth, a large-scale multitemporal dataset designed to pretrain hyperspectral foundation models.<n>We pretrain a series of foundation models on SpectralEarth, integrating a spectral adapter into classical vision backbones.<n>In tandem, we construct nine downstream datasets for land-cover, crop-type mapping, and tree-species classification.
  arXiv  Detail & Related papers  (2024-08-15T22:55:59Z)
• Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View [49.03501451546763]
  We identify the importance of implicit correspondences across biological contexts for exploiting domain-invariant pathological composition. We propose self-adaptive dynamic distillation to secure instance-aware trade-offs across different model constituents.
  arXiv  Detail & Related papers  (2024-07-14T04:41:16Z)
• Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders [50.689585476660554]
  We propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models.
  arXiv  Detail & Related papers  (2022-12-14T06:04:18Z)
• ScoreNet: Learning Non-Uniform Attention and Augmentation for Transformer-Based Histopathological Image Classification [11.680355561258427]
  High-resolution images hinder progress in digital pathology. patch-based processing often incorporates multiple instance learning (MIL) to aggregate local patch-level representations yielding image-level prediction. This paper proposes a transformer-based architecture specifically tailored for histological image classification. It combines fine-grained local attention with a coarse global attention mechanism to learn meaningful representations of high-resolution images at an efficient computational cost.
  arXiv  Detail & Related papers  (2022-02-15T16:55:09Z)
• Chest x-ray automated triage: a semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures [83.48996461770017]
  This work presents a Deep Learning method based on the late fusion of different convolutional architectures. We built four training datasets combining images from public chest x-ray datasets and our institutional archive. We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool.
  arXiv  Detail & Related papers  (2020-12-23T14:38:35Z)
• Pollen13K: A Large Scale Microscope Pollen Grain Image Dataset [63.05335933454068]
  This work presents the first large-scale pollen grain image dataset, including more than 13 thousands objects. The paper focuses on the employed data acquisition steps, which include aerobiological sampling, microscope image acquisition, object detection, segmentation and labelling.
  arXiv  Detail & Related papers  (2020-07-09T10:33:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.