RE-Tagger: A light-weight Real-Estate Image Classifier

TL;DR

RE-Tagger is a lightweight, end-to-end real-estate image classification pipeline using transfer learning with a custom InceptionV3 model, providing an accessible web API for categorizing property images.

Contribution

The paper introduces a novel, efficient transfer learning-based approach for real-estate image classification and releases a practical web API implementation.

Findings

High accuracy in classifying property images

Low resource requirements for deployment

Effective for real-time applications

Abstract

Real-estate image tagging is one of the essential use-cases to save efforts involved in manual annotation and enhance the user experience. This paper proposes an end-to-end pipeline (referred to as RE-Tagger) for the real-estate image classification problem. We present a two-stage transfer learning approach using custom InceptionV3 architecture to classify images into different categories (i.e., bedroom, bathroom, kitchen, balcony, hall, and others). Finally, we released the application as REST API hosted as a web application running on 2 cores machine with 2 GB RAM. The demo video is available here.