datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
HUGO-Bench
HUGO-Bench
Hierarchical Unsupervised Grouping of Organisms Benchmark
A comprehensive benchmark dataset for evaluating zero-shot clustering of wildlife camera trap images using Vision Transformer embeddings.
Overview
HUGO-Bench contains 139,111 expert-validated cropped images of 60 animal species (30 birds, 30 mammals), derived from 23 camera trap projects across LILA BC. The dataset enables benchmarking of Vision Transformer models for unsupervised species-level… See the full description on the dataset page: https://huggingface.co/datasets/AI-EcoNet/HUGO-Bench.m-hood-dataset
M-Hood Dataset: Out-of-Distribution Evaluation Collection
This dataset collection contains out-of-distribution (OOD) image datasets specifically curated for evaluating the robustness of object detection models, particularly those trained to mitigate hallucination on out-of-distribution data.
🎯 Purpose
These datasets are designed to address limitations in existing OOD benchmarks and enable fine-grained analysis of hallucination suppression. They test how well object… See the full description on the dataset page: https://huggingface.co/datasets/HugoHE/m-hood-dataset.CIFAR100-Blended-20pct-Backdoor-ExclNaturalCIFAR100-Blended-20pct-BackdoorCIFAR100-Random-2x2-Backdoor-ExclNaturaldebussy-omr-fullpage-lvl
Debussy OMR – Full-Page Level Dataset
A dataset of 101 paired samples of full-page images from handwritten music scores written by Claude Debussy (French Composer, 1862 - 1918) and their corresponding MusicXML transcriptions.
The manuscript images originate from the collections of the Bibliothèque nationale de France (BnF) and were accessed through the IIIF protocol.
Dataset Description
Property
Value
Samples
101
Documents
37
Image format
JPEG… See the full description on the dataset page: https://huggingface.co/datasets/HugoSchtr/debussy-omr-fullpage-lvl.MNIST-Patch-1x1-BackdoorCIFAR100-Blended-5pct-Backdoordebussy-omr-system-lvl
Debussy OMR – System-Level Dataset
A dataset of 491 paired samples of cropped system images from handwritten music scores written by Claude Debussy (French Composer, 1862 - 1918) and their corresponding MusicXML transcriptions.
The manuscript images originate from the collections of the Bibliothèque nationale de France (BnF) and were accessed through the IIIF protocol.
Dataset Description
Property
Value
Samples
491
Documents
37
Pages
101
Image format… See the full description on the dataset page: https://huggingface.co/datasets/HugoSchtr/debussy-omr-system-lvl.defacement-detection-balancedCIFAR100-Blended-5pct-Backdoor-ExclNaturalCIFAR10-Patch-2x2-BackdoorCIFAR10-Blended-20pct-Backdoor-ExclNaturalMNIST-Patch-2x2-BackdoorCIFAR10-Random-2x2-Backdoorhugo_jackets_ds
Dataset Card for "hugo_jackets_ds"
More Information needed
MNIST-Patch-3x3-BackdoorCIFAR10-Random-4x4-BackdoorCIFAR10-Random-3x3-BackdoorMNIST-Patch-4x4-BackdoorCIFAR100-Random-2x2-BackdoorCIFAR10-Adversarial-PGD-Untargeted-Eps0p03137hugo_dresses_ds
Dataset Card for "hugo_dresses_ds"
More Information needed
hugo_suits_ds
Dataset Card for "hugo_suits_ds"
More Information needed
hugo_tsne_ds
Dataset Card for "hugo_tsne_ds"
More Information needed
CIFAR10-Adversarial-PGD-Targeted-Class0-Eps0p03137hugospacegood
