Published 2026 | Version v3
Dataset Open

MassID45: Mixed Arthropod Sample Segmentation and Identification

Description

A dataset for training automatic classifiers of bulk insect samples, using both molecular and imaging data. DNA barcodes and images are available at both the unsorted sample level and the full set of individual specimens from those samples.

Further information about the dataset is available in the pre-print: A multi-modal dataset for insect biodiversity with imagery and DNA at the trap and individual level. Code for preprocessing and training/inference is available at https://github.com/uoguelph-mlrg/MassID45.    

Files

annotation_tiles.zip

Files (7.1 GB)

Name Size Download all
md5:91c2875a4692041b7651c1ce00a41253
312.1 MB Preview Download
md5:72983812fa2cb74d48caaeb732de0fde
110.1 MB Preview Download
md5:13815dcb4a46272fe74da4c5ebf04fc0
127.4 MB Preview Download
md5:5ff4e9131d748ac2b6e28d63b1639889
32.9 MB Preview Download
md5:2c41f72bd08f09eb7b013be0910e813f
47.3 MB Preview Download
md5:8d515342c8bf811789b797df4240b9f0
28.7 MB Preview Download
md5:bad8b28ff165ce5cfba31395483b3e76
493.8 MB Preview Download
md5:6519d46850e1fb396a1b8d92f481e590
2.4 GB Preview Download
md5:51ced1901e03a92ffcf8f1726867ce54
1.1 GB Preview Download
md5:8b3025b3404ae0dc2d682160956ec313
866.3 MB Preview Download
md5:07da61d90c2eb11ace34344008d13a5f
3.9 kB Preview Download
md5:71dade8ae649a07290f7fbb00af52841
4.5 kB Preview Download
md5:9e432f5de99deaffa2afbbb3463d90f4
1.5 GB Preview Download

Additional details

Dates

Updated
2026-01-16
Added cropped and tiled bulk images.