Cuteness Classifier

Overview

Cuteness Classifier is a two-stage machine learning pipeline that first classifies whether an image contains a dog or a cat, then assigns a cuteness score to the animal — comparing AI ratings against human perception.

Pipeline

1. 1Image ingestion and preprocessing (resize, normalize)
2. 2Binary classification: dog vs. cat using a trained CNN
3. 3Cuteness scoring: regression model outputs a 1–10 rating
4. 4Human comparison: AI scores benchmarked against human rankings

Results

The model demonstrated strong alignment with human cuteness rankings, particularly for cats. The project illustrates end-to-end ML workflows from data preprocessing to evaluation and human-in-the-loop comparison.