Back to datasets
Dataset assetOpen Source CommunityObject DetectionBird Species Recognition
HiFSOD-Bird
HiFSOD‑Bird is the first dataset for the HIFSOD problem. It contains 176,350 wild bird images, divided into 1,432 categories, organized into a four‑level taxonomy comprising 32 orders, 132 families, 572 genera, and 1,432 species.
Source
github
Created
Jul 9, 2022
Updated
Nov 23, 2022
Signals
504 views
Availability
Linked source ready
Overview
Dataset description and usage context
Dataset Overview
- Name: HiFSOD‑Bird
- Type: The first dataset for Hierarchical Few‑Shot Object Detection (HIFSOD)
- Content: Contains 176,350 wild bird images, divided into 1,432 categories organized into a four‑level taxonomy with 32 orders, 132 families, 572 genera, and 1,432 species.
- Download Link: Google Driver
Citation Information
- Paper: Zhang, Lu et al. "Hierarchical Few‑Shot Object Detection: Problem, Benchmark and Method." Proceedings of the 30th ACM International Conference on Multimedia. 2022.
- Citation Format:
@inproceedings{10.1145/3503161.3548412,
author = {Zhang, Lu and Wang, Yang and Zhou, Jiaogen and Zhang, Chenbo and Zhang, Yinglu and Guan, Jihong and Bian, Yatao and Zhou, Shuigeng},
title = {Hierarchical Few‑Shot Object Detection: Problem, Benchmark and Method},
year = {2022},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3503161.3548412},
doi = {10.1145/3503161.3548412},
booktitle = {Proceedings of the 30th ACM International Conference on Multimedia},
pages = {2002–2011},
location = {Lisboa, Portugal},
series = {MM 22}
}
Need downstream help?
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.