Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.03182 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916777294823424 |
|---|---|
| author | Chiranjeevi, Shivani Zaremehrjerdi, Hossein Deng, Zi K. Jubery, Talukder Z. Grele, Ari Singh, Arti Singh, Asheesh K Sarkar, Soumik Merchant, Nirav Greeney, Harold F. Ganapathysubramanian, Baskar Hegde, Chinmay |
| author_facet | Chiranjeevi, Shivani Zaremehrjerdi, Hossein Deng, Zi K. Jubery, Talukder Z. Grele, Ari Singh, Arti Singh, Asheesh K Sarkar, Soumik Merchant, Nirav Greeney, Harold F. Ganapathysubramanian, Baskar Hegde, Chinmay |
| contents | The rapid global loss of biodiversity, particularly among insects, represents an urgent ecological crisis. Current methods for insect species discovery are manual, slow, and severely constrained by taxonomic expertise, hindering timely conservation actions. We introduce TerraIncognita, a dynamic benchmark designed to evaluate state-of-the-art multimodal models for the challenging problem of identifying unknown, potentially undescribed insect species from image data. Our benchmark dataset combines a mix of expertly annotated images of insect species likely known to frontier AI models, and images of rare and poorly known species, for which few/no publicly available images exist. These images were collected from underexplored biodiversity hotspots, realistically mimicking open-world discovery scenarios faced by ecologists. The benchmark assesses models' proficiency in hierarchical taxonomic classification, their capability to detect and abstain from out-of-distribution (OOD) samples representing novel species, and their ability to generate explanations aligned with expert taxonomic knowledge. Notably, top-performing models achieve over 90\% F1 at the Order level on known species, but drop below 2\% at the Species level, highlighting the sharp difficulty gradient from coarse to fine taxonomic prediction (Order $\rightarrow$ Family $\rightarrow$ Genus $\rightarrow$ Species). TerraIncognita will be updated regularly, and by committing to quarterly dataset expansions (of both known and novel species), will provide an evolving platform for longitudinal benchmarking of frontier AI methods. All TerraIncognita data, results, and future updates are available \href{https://baskargroup.github.io/TerraIncognita/}{here}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TerraIncognita: A Dynamic Benchmark for Species Discovery Using Frontier Models Chiranjeevi, Shivani Zaremehrjerdi, Hossein Deng, Zi K. Jubery, Talukder Z. Grele, Ari Singh, Arti Singh, Asheesh K Sarkar, Soumik Merchant, Nirav Greeney, Harold F. Ganapathysubramanian, Baskar Hegde, Chinmay Computer Vision and Pattern Recognition Machine Learning The rapid global loss of biodiversity, particularly among insects, represents an urgent ecological crisis. Current methods for insect species discovery are manual, slow, and severely constrained by taxonomic expertise, hindering timely conservation actions. We introduce TerraIncognita, a dynamic benchmark designed to evaluate state-of-the-art multimodal models for the challenging problem of identifying unknown, potentially undescribed insect species from image data. Our benchmark dataset combines a mix of expertly annotated images of insect species likely known to frontier AI models, and images of rare and poorly known species, for which few/no publicly available images exist. These images were collected from underexplored biodiversity hotspots, realistically mimicking open-world discovery scenarios faced by ecologists. The benchmark assesses models' proficiency in hierarchical taxonomic classification, their capability to detect and abstain from out-of-distribution (OOD) samples representing novel species, and their ability to generate explanations aligned with expert taxonomic knowledge. Notably, top-performing models achieve over 90\% F1 at the Order level on known species, but drop below 2\% at the Species level, highlighting the sharp difficulty gradient from coarse to fine taxonomic prediction (Order $\rightarrow$ Family $\rightarrow$ Genus $\rightarrow$ Species). TerraIncognita will be updated regularly, and by committing to quarterly dataset expansions (of both known and novel species), will provide an evolving platform for longitudinal benchmarking of frontier AI methods. All TerraIncognita data, results, and future updates are available \href{https://baskargroup.github.io/TerraIncognita/}{here}. |
| title | TerraIncognita: A Dynamic Benchmark for Species Discovery Using Frontier Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.03182 |