Semantics Disentangling for Text-to-Image Generation
This work addresses the problem of inconsistent semantics in text-to-image generation for AI and computer vision applications, representing an incremental improvement.
The paper tackles the challenge of synthesizing photo-realistic images from text descriptions by addressing inconsistent semantics from diverse linguistic expressions, proposing a model that disentangles semantics to achieve high-level consistency and low-level diversity, with experiments on CUB and MS-COCO datasets showing superiority over state-of-the-art methods.
Synthesizing photo-realistic images from text descriptions is a challenging problem. Previous studies have shown remarkable progresses on visual quality of the generated images. In this paper, we consider semantics from the input text descriptions in helping render photo-realistic images. However, diverse linguistic expressions pose challenges in extracting consistent semantics even they depict the same thing. To this end, we propose a novel photo-realistic text-to-image generation model that implicitly disentangles semantics to both fulfill the high-level semantic consistency and low-level semantic diversity. To be specific, we design (1) a Siamese mechanism in the discriminator to learn consistent high-level semantics, and (2) a visual-semantic embedding strategy by semantic-conditioned batch normalization to find diverse low-level semantics. Extensive experiments and ablation studies on CUB and MS-COCO datasets demonstrate the superiority of the proposed method in comparison to state-of-the-art methods.