Published May 30, 2023 | Version v1
Dataset Open

Out-of-distribution detection algorithms for robust insect classification dataset and models

Authors/Creators

  • 1. Iowa State University

Description

This folder contains trained models and datasets for reproducing the results in the paper on out-of-distribution detection algorithms for robust insect classification. Specifically, it contains the following folders: 

 

  • OODInsect (out-of-distribution data)
  • MSP, MAH, and EBM trained models, each wrapped around the three classifiers of ResNet50, RegNet32, and VGG11, and different combinations of ID and OOD test data for reproducing RQ1, RQ2, and RQ3.
  • ID3 (in-distribution test data)

Files

iNat-OOD-Dataset-Models.zip

Files (49.3 GB)

Name Size
md5:2ef7920e6d5d1f280f1d9a808c5510d4
49.3 GB Preview Download

Additional details

Funding

U.S. National Science Foundation
CPS: Frontier: Collaborative Research: COALESCE: COntext Aware LEarning for Sustainable CybEr-Agricultural Systems 1954556
U.S. National Science Foundation
SCC-IRG Track 2: Smart Integrated Farm Network for Rural Agricultural Communities (SIRAC) 1952045