Deep Generative Neural Embeddings for High Dimensional Data Visualization
This is an incremental improvement for researchers and practitioners in data visualization, offering more flexibility than traditional autoencoders.
The paper tackles high-dimensional data visualization by proposing a generative neural embedding technique that allows independent manipulation of image embeddings, demonstrating scalability on ImageNet and comparing favorably to t-SNE and VAE methods.
We propose a visualization technique that utilizes neural network embeddings and a generative network to reconstruct original data. This method allows for independent manipulation of individual image embeddings through its non-parametric structure, providing more flexibility than traditional autoencoder approaches. We have evaluated the effectiveness of this technique in data visualization and compared it to t-SNE and VAE methods. Furthermore, we have demonstrated the scalability of our method through visualizations on the ImageNet dataset. Our technique has potential applications in human-in-the-loop training, as it allows for independent editing of embedding locations without affecting the optimization process.