五美元模型:从句子嵌入生成游戏地图和精灵图
The Five-Dollar Model: Generating Game Maps and Sprites from Sentence Embeddings
AI总结:
本文提出轻量级文本到图像模型“五美元模型”,利用句子嵌入在像素地图、精灵图和表情符号等小数据集上生成低维图像,并通过新颖增强策略和 CLIP 余弦相似度验证其语义保持能力。
摘要:
五美元模型是一种轻量级的文本到图像生成架构,能够从编码后的文本提示生成低维图像。该模型可以在低维领域中,利用有限的训练数据成功生成准确且美观的内容。尽管模型和数据集规模都很小,生成的图像仍能保持文本提示中编码的语义含义。我们将该模型应用于三个小型数据集:像素艺术视频游戏地图、视频游戏精灵图像和降采样表情符号图像,并采用新颖的数据增强策略来提升模型在这些有限数据集上的性能。我们使用 CLIP VIT-B/32 模型生成的文本-图像对之间的余弦相似度分数来评估模型性能。
英文摘要:
The five-dollar model is a lightweight text-to-image generative architecture that generates low dimensional images from an encoded text prompt. This model can successfully generate accurate and aesthetically pleasing content in low dimensional domains, with limited amounts of training data. Despite the small size of both the model and datasets, the generated images are still able to maintain the encoded semantic meaning of the textual prompt. We apply this model to three small datasets: pixel art video game maps, video game sprite images, and down-scaled emoji images and apply novel augmentation strategies to improve the performance of our model on these limited datasets. We evaluate our models performance using cosine similarity score between text-image pairs generated by the CLIP VIT-B/32 model.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。