Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space
This addresses the issue of generating varied and precise image descriptions for applications like accessibility or content indexing, though it is incremental as it builds on existing CVAE methods.
The paper tackled the problem of low variability in image captions generated by standard conditional variational auto-encoders by proposing two models with structured latent spaces using Gaussian Mixture and Additive Gaussian priors, resulting in captions that are more diverse and accurate than baselines, with the AG-CVAE showing particular promise.
This paper explores image caption generation using conditional variational auto-encoders (CVAEs). Standard CVAEs with a fixed Gaussian prior yield descriptions with too little variability. Instead, we propose two models that explicitly structure the latent space around $K$ components corresponding to different types of image content, and combine components to create priors for images that contain multiple types of content simultaneously (e.g., several kinds of objects). Our first model uses a Gaussian Mixture model (GMM) prior, while the second one defines a novel Additive Gaussian (AG) prior that linearly combines component means. We show that both models produce captions that are more diverse and more accurate than a strong LSTM baseline or a "vanilla" CVAE with a fixed Gaussian prior, with AG-CVAE showing particular promise.