paper-with-me

홈 › Papers

CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale

2024-05-27 · ZeMing Gong, Austin T. Wang, Xiaoliang Huo, Joakim Bruslund Haurum, Scott C. Lowe, Graham W. Taylor, Angel X. Chang

Measuring biodiversity is crucial for understanding ecosystem health. While prior works have developed machine learning models for taxonomic classification of photographic images and DNA separately, in this work, we introduce a multimodal approach combining both, using CLIP-style contrastive learning to align images, barcode DNA, and text-based representations of taxonomic labels in a unified embedding space. This allows for accurate classification of both known and unknown insect species without task-specific fine-tuning, leveraging contrastive learning for the first time to fuse DNA and image data. Our method surpasses previous single-modality approaches in accuracy by over 8% on zero-shot learning tasks, showcasing its effectiveness in biodiversity studies.

📄 PDF Abstract BibTeX arXiv:2405.17537

Code (4)

3dlg-hcvc/bioscan-clip 공식 구현 pytorch
VectorInstitute/mmlearn/tree/main/projects/bioscan_clip pytorch
bioscan-ml/bioscan-5m
bioscan-ml/dataset pytorch

Tasks

Contrastive LearningZero-Shot Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference

2026-03-26 · Sk Miraj Ahmed, Xi Yu, Yunqi Li, Yuewei Lin 외 arxiv

Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, the core task is taxonomic prediction - i…

Representation Learning

Open-Set Recognition of Novel Species in Biodiversity Monitoring

2025-03-03 · Yuyan Chen, Nico Lang, B. Christian Schmidt, Aditya Jain 외

Machine learning is increasingly being applied to facilitate long-term, large-scale biodiversity monitoring. With most species on Earth still undiscovered or poorly documented, species-recognition models are expected to …

Fine-Grained Image RecognitionOpen Set LearningOut-of-Distribution Detection

Guide to k-mer approaches for genomics across the tree of life

2024-04-01 · Katharine M. Jenike, Lucía Campos-Domínguez, Marilou Boddé, José Cerca 외

The wide array of currently available genomes display a wonderful diversity in size, composition and structure with many more to come thanks to several global biodiversity genomics initiatives starting in recent years. H…

Diversity

Automated Detection of Antarctic Benthic Organisms in High-Resolution In Situ Imagery to Aid Biodiversity Monitoring

2025-07-29 · Cameron Trotter, Huw Griffiths, Tasnuva Ming Khan, Rowan Whittle arxiv

Monitoring benthic biodiversity in Antarctica is vital for understanding ecological change in response to climate-driven pressures. This work is typically performed using high-resolution imagery captured in situ, though …

Data AugmentationObject Detection

BarcodeMamba+: Advancing State-Space Models for Fungal Biodiversity Research

2025-12-17 · Tiancheng Gao, Scott C. Lowe, Brendan Furneaux, Angel X Chang 외 arxiv

Accurate taxonomic classification from DNA barcodes is a cornerstone of global biodiversity monitoring, yet fungi present extreme challenges due to sparse labelling and long-tailed taxa distributions. Conventional superv…