Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images

Kazi Sajeed Mehrab, M. Maruf, Arka Daw, Harish Babu Manogaran, Abhilash Neog +13 more
2/9/2026

No official code found. Best implementation: Imageomics/Fish-Vista (8 stars, MIT, last commit 2026-02-05).

Abstract

We introduce Fish-Visual Trait Analysis (Fish-Vista), the first organismal image dataset designed for the analysis of visual traits of aquatic species directly from images using machine learning and computer vision methods. Fish-Vista contains 69,269 annotated images spanning 4,316 fish species, curated and organized to serve three downstream tasks: species classification, trait identification, and trait segmentation. Our work makes two key contributions. First, we provide a fully reproducible data processing pipeline to process fish images sourced from various museum collections, contributing to the advancement of AI in biodiversity science. We annotate the images with carefully curated labels from biological databases and manual annotations to create an AI-ready dataset of visual traits. Second, our work offers fertile grounds for researchers to develop novel methods for a variety of problems in computer vision such as handling long-tailed distributions, out-of-distribution generalization, learning with weak labels, explainable AI, and segmenting small objects. Dataset and code for Fish-Vista are available at https://github.com/Imageomics/Fish-Vista

View on arXivView PDF

Code Implementations(1)

Imageomics/Fish-VistaCommunity100%
MIT

Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images

81Shell, PythonJun 25, 20248 months agoMIT
datafishspecimen-imagestrait-identificationtraits

Similar Papers

FishNet: A Large-scale Dataset and Benchmark for Fish Recognition, Detection, and Functional Trait Prediction

86% match2026

FishNet: Deep Neural Networks for Low-Cost Fish Stock Estimation

86% match2024

Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding

86% match1 repo142024

Optimizing Image Capture for Computer Vision-Powered Taxonomic Identification and Trait Recognition of Biodiversity Specimens

84% match1 repo2025

Detecting Endangered Marine Species in Autonomous Underwater Vehicle Imagery Using Point Annotations and Few-Shot Learning

84% match2024

ORCA: Object Recognition and Comprehension for Archiving Marine Species

83% match2025

Cite this paper

@article{mehrab2026fishvista,
  title  = {Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images},
  author = {Kazi Sajeed Mehrab and M. Maruf and Arka Daw and Harish Babu Manogaran and Abhilash Neog and Mridul Khurana and B. Altıntaş and Yasin Bakiş and Elizabeth G. Campolongo and Matthew J. Thompson and Xiaojun Wang and H. Lapp and Wei-Lun Chao and Paula M. Mabee and Henry L. Bart and W. Dahdul and A. Karpatne and Virginia Tech},
  year   = {2026},
  eprint = {2407.08027},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2407.08027},
  journal = {CVPR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.08027.svg)](https://codeofpaper.com/paper/2407.08027)

Discussion