🐼太真实
(2023-12-28 20:39):
#paper https://doi.org/10.48550/arXiv.2312.03701 , Self-conditioned Image Generation via Generating Representations
这篇文章介绍了一种名为“表示条件图像生成”（RCG）的新型图像生成框架。RCG 不依赖于人类标注，而是基于自监督的表示分布来生成图像。使用预训练的编码器将图像分布映射到表示分布，然后通过表示扩散模型（RDM）从中采样，最后通过像素生成器根据采样的表示生成图像。RCG 在 ImageNet 256×256 数据集上实现了显著的性能提升，其 FID 和 IS 分别达到了 3.31 和 253.4。这个方法不仅显著提升了类无条件图像生成的水平，而且与当前领先的类条件图像生成方法相比也具有竞争力，弥补了这两种任务之间长期存在的性能差距。
arXiv,
2023.
DOI: 10.48550/arXiv.2312.03701
Self-conditioned Image Generation via Generating Representations
Tianhong Li,
Dina Katabi,
Kaiming He
Abstract:
This paper presents $\textbf{R}$epresentation-$\textbf{C}$onditioned image<br>$\textbf{G}$eneration (RCG), a simple yet effective image generation framework<br>which sets a new benchmark in class-unconditional image generation. RCG does<br>not condition on any human annotations. Instead, it conditions on a<br>self-supervised representation distribution which is mapped from the image<br>distribution using a pre-trained encoder. During generation, RCG samples from<br>such representation distribution using a representation diffusion model (RDM),<br>and employs a pixel generator to craft image pixels conditioned on the sampled<br>representation. Such a design provides substantial guidance during the<br>generative process, resulting in high-quality image generation. Tested on<br>ImageNet 256$\times$256, RCG achieves a Frechet Inception Distance (FID) of<br>3.31 and an Inception Score (IS) of 253.4. These results not only significantly<br>improve the state-of-the-art of class-unconditional image generation but also<br>rival the current leading methods in class-conditional image generation,<br>bridging the long-standing performance gap between these two tasks. Code is<br>available at https://github.com/LTH14/rcg.
Related Links: