Memory-Driven Text-to-Image Generation
This work addresses the problem of generating realistic images from text descriptions for applications in AI and computer vision, representing an incremental improvement over existing methods.
The paper tackles text-to-image generation by introducing a memory-driven semi-parametric approach that combines a memory bank of image features with a generative adversarial network, resulting in more realistic images with improved visual fidelity and text-image semantic consistency compared to purely parametric methods.
We introduce a memory-driven semi-parametric approach to text-to-image generation, which is based on both parametric and non-parametric techniques. The non-parametric component is a memory bank of image features constructed from a training set of images. The parametric component is a generative adversarial network. Given a new text description at inference time, the memory bank is used to selectively retrieve image features that are provided as basic information of target images, which enables the generator to produce realistic synthetic results. We also incorporate the content information into the discriminator, together with semantic features, allowing the discriminator to make a more reliable prediction. Experimental results demonstrate that the proposed memory-driven semi-parametric approach produces more realistic images than purely parametric approaches, in terms of both visual fidelity and text-image semantic consistency.