ノイズ除去拡散確率モデル
Denoising Diffusion Probabilistic Models
※ 解説はAIが生成。被引用数はOpenAlex由来(取得できた論文のみ表示)。詳細は原論文をご確認ください。
非平衡熱力学に着想を得た拡散確率モデルで高品質な画像生成を実現し、CIFAR10で最先端のFIDスコア3.17を達成した論文。
著者: Jonathan Ho, Ajay Jain, P. Abbeel
分類: landmark
原文アブストラクト
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. Our implementation is available at this https URL
関連論文基盤技術(ロボット基盤モデルが依拠)
- 自然言語による教師あり学習で汎用的な視覚モデルを学ぶ視覚言語モデル
- アテンションこそがすべて自然言語処理
