Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟯𝟬 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗘𝗶𝗴𝗲𝗻𝗚𝗔𝗡: Layer-Wise Eigen-Learning for GANs by Peng Cheng Laboratory, China Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published in ICCV2021with 3 citation. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eHgmfhyS Code : https://lnkd.in/eK85Yehq ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Recent studies on Generative Adversarial Network (GAN) reveal that different layers of a generative CNN hold different semantics of the synthesized images. However, few GAN models have explicit dimensions to control the semantic attributes represented in a specific layer. 🔸This paper proposes EigenGAN which is able to unsupervisedly mine interpretable and controllable dimensions from different generator layers. Specifically, EigenGAN embeds one linear subspace with orthogonal basis into each generator layer. 🔸Via generative adversarial training to learn a target distribution, these layer-wise subspaces automatically discover a set of "eigen-dimensions" at each layer corresponding to a set of semantic attributes or interpretable variations. 🔸By traversing the coefficient of a specific eigen-dimension, the generator can produce samples with continuous changes corresponding to a specific semantic attribute. Taking the human face for example, EigenGAN can discover controllable dimensions for high-level concepts such as pose and gender in the subspace of deep layers, as well as low-level concepts such as hue and color in the subspace of shallow layers. 🔸Moreover, in the linear case, we theoretically prove that our algorithm derives the principal components as PCA does. #computervision #artificialintelligence #data