PETS-SWINF: A regression method that considers images with metadata based Neural Network for pawpularity prediction on 2021 Kaggle Competition "PetFinder.my"

TL;DR

PETS-SWINF is a novel neural network model that effectively integrates image data and metadata to predict pawpularity scores of animals, outperforming image-only models in a Kaggle competition.

Contribution

The paper introduces PETS-SWINF, a new regression method that considers both images and metadata, addressing a gap in existing animal pawpularity prediction models.

Findings

Achieved a lower RMSE with metadata (17.71876) than without (17.76449).

Ranked 15th out of 3545 teams in the Kaggle competition.

Demonstrated the model's ability to adaptively weight image and metadata features.

Abstract

Millions of stray animals suffer on the streets or are euthanized in shelters every day around the world. In order to better adopt stray animals, scoring the pawpularity (cuteness) of stray animals is very important, but evaluating the pawpularity of animals is a very labor-intensive thing. Consequently, there has been an urgent surge of interest to develop an algorithm that scores pawpularity of animals. However, the dataset in Kaggle not only has images, but also metadata describing images. Most methods basically focus on the most advanced image regression methods in recent years, but there is no good method to deal with the metadata of images. To address the above challenges, the paper proposes an image regression model called PETS-SWINF that considers metadata of the images. Our results based on a dataset of Kaggle competition, "PetFinder.my", show that PETS-SWINF has an advantage over only based images models. Our results shows that the RMSE loss of the proposed model on the test dataset is 17.71876 but 17.76449 without metadata. The advantage of the proposed method is that PETS-SWINF can consider both low-order and high-order features of metadata, and adaptively adjust the weights of the image model and the metadata model. The performance is promising as our leadboard score is ranked 15 out of 3545 teams (Gold medal) currently for 2021 Kaggle competition on the challenge "PetFinder.my".