# How many images do I need? Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring

arXiv: https://arxiv.org/abs/2010.08186 · HTML: https://mlsanity.com/paper/2010.08186/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 11 of 11)

- [Deep Learning for Survival Analysis: A Review](https://mlsanity.com/paper/2305.14961/) (2023)
- [Iterative Human and Automated Identification of Wildlife Images](https://mlsanity.com/paper/2105.02320/) (2021)
- [Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models](https://mlsanity.com/paper/2503.07329/) (2025)
- [Mask Usage Recognition using Vision Transformer with Transfer Learning and Data Augmentation](https://mlsanity.com/paper/2203.11542/) (2022)
- [Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices](https://mlsanity.com/paper/2603.29375/) (2026)
- [A study of CNN capacity applied to Left Venticle Segmentation in Cardiac MRI](https://mlsanity.com/paper/2107.01318/) (2021)
- [A workflow for segmenting soil and plant X-ray CT images with deep learning in Googles Colaboratory](https://mlsanity.com/paper/2203.09674/) (2022)
- [Trustworthiness of Laser-Induced Breakdown Spectroscopy Predictions via Simulation-based Synthetic Data Augmentation and Multitask Learning](https://mlsanity.com/paper/2210.03762/) (2022)
- [Sample size determination for machine learning in medical research](https://mlsanity.com/paper/2503.05809/) (2025)
- [Generative Dataset Distillation using Min-Max Diffusion Model](https://mlsanity.com/paper/2503.18626/) (2025)
- [Towards Edge-Based Idle State Detection in Construction Machinery Using Surveillance Cameras](https://mlsanity.com/paper/2506.00904/) (2025)

## Abstract (arXiv)

Deep learning (DL) algorithms are the state of the art in automated classification of wildlife camera trap images. The challenge is that the ecologist cannot know in advance how many images per species they need to collect for model training in order to achieve their desired classification accuracy. In fact there is limited empirical evidence in the context of camera trapping to demonstrate that increasing sample size will lead to improved accuracy. In this study we explore in depth the issues of deep learning model performance for progressively increasing per class (species) sample sizes. We also provide ecologists with an approximation formula to estimate how many images per animal species they need for certain accuracy level a priori. This will help ecologists for optimal allocation of resources, work and efficient study design. In order to investigate the effect of number of training images; seven training sets with 10, 20, 50, 150, 500, 1000 images per class were designed. Six deep learning architectures namely ResNet-18, ResNet-50, ResNet-152, DnsNet-121, DnsNet-161, and DnsNet-201 were trained and tested on a common exclusive testing set of 250 images per class. The whole experiment was repeated on three similar datasets from Australia, Africa and North America and the results were compared. Simple regression equations for use by practitioners to approximate model performance metrics are provided. Generalized additive models (GAM) are shown to be effective in modelling DL performance metrics based on the number of training images per class, tuning scheme and dataset. Key-words: Camera Traps, Deep Learning, Ecological Informatics, Generalised Additive Models, Learning Curves, Predictive Modelling, Wildlife.