# A Hybrid Supervised-unsupervised Method on Image Topic Visualization with Convolutional Neural Network and LDA

## TL;DR

This paper introduces a hybrid method combining CNN and LDA to visualize image topics from unlabeled datasets, significantly improving topic consistency and enabling scalable analysis with parallel processing.

## Contribution

It presents a novel hybrid supervised-unsupervised approach integrating AlexNet and LDA for image topic visualization without extensive manual labeling.

## Key findings

- Achieves 84% consistent rate compared to 18.75% from raw CNN
- Capable of detecting false labels and multi-labels in datasets
- Scalable to large datasets with parallel processing, extracting 1,000 topics in 10 minutes

## Abstract

Given the progress in image recognition with recent data driven paradigms, it's still expensive to manually label a large training data to fit a convolutional neural network (CNN) model. This paper proposes a hybrid supervised-unsupervised method combining a pre-trained AlexNet with Latent Dirichlet Allocation (LDA) to extract image topics from both an unlabeled life-logging dataset and the COCO dataset. We generate the bag-of-words representations of an egocentric dataset from the softmax layer of AlexNet and use LDA to visualize the subject's living genre with duplicated images. We use a subset of COCO on 4 categories as ground truth, and define consistent rate to quantitatively analyze the performance of the method, it achieves 84% for consistent rate on average comparing to 18.75% from a raw CNN model. The method is capable of detecting false labels and multi-labels from COCO dataset. For scalability test, parallelization experiments are conducted with Harp-LDA on a Intel Knights Landing cluster: to extract 1,000 topic assignments for 241,035 COCO images, it takes 10 minutes with 60 threads.