Quantification in-the-wild: data-sets and baselines

2015/10/16 by Oscar Beijbom, Judy Hoffman, Beijbom, Oscar +11 · 1 citation
Computer Science · Physics and Astronomy · #Complex Network Analysis Techniques #Data Stream Mining Techniques #Data Visualization and Analytics #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1510.04811

openalex publication_date 2015/10/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Quantification is the task of estimating the class-distribution of a data-set. While typically considered as a parameter estimation problem with strict assumptions on the data-set shift, we consider quantification in-the-wild, on two large scale data-sets from marine ecology: a survey of Caribbean coral reefs, and a plankton time series from Martha's Vineyard Coastal Observatory. We investigate several quantification methods from the literature and indicate opportunities for future work. In particular, we show that a deep neural network can be fine-tuned on a very limited amount of data (25 - 100 samples) to outperform alternative methods.

Citations

• Adjusting the Outputs of a Classifier to New aPrioriProbabilities: A Simple Procedure
• WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classification
• Caffe: Convolutional Architecture for Fast Feature Embedding

Cited by

• On the Interconnections of Calibration, Quantification, and Classifier Accuracy Prediction under Dataset Shift

Related

• Unlocking the potential of deep learning for marine ecology: overview,\n applications, and outlook
• Deep learning for Plankton and Coral Classification
• The FathomNet2023 Competition Dataset
• Correcting misclassification errors in crowdsourced ecological data: A\n Bayesian perspective
• Integrating Deep Learning and Spatial Statistics in Marine Ecosystem Monitoring