Image Manipulation with Perceptual Discriminators
This work addresses image manipulation for computer vision applications, offering an incremental improvement by integrating existing loss types more effectively.
The paper tackles the problem of unaligned image translation by combining perceptual and adversarial losses in a non-additive way, resulting in a new perceptual discriminator architecture that improves performance over baseline and state-of-the-art methods in qualitative and quantitative comparisons.
Systems that perform image manipulation using deep convolutional networks have achieved remarkable realism. Perceptual losses and losses based on adversarial discriminators are the two main classes of learning objectives behind these advances. In this work, we show how these two ideas can be combined in a principled and non-additive manner for unaligned image translation tasks. This is accomplished through a special architecture of the discriminator network inside generative adversarial learning framework. The new architecture, that we call a perceptual discriminator, embeds the convolutional parts of a pre-trained deep classification network inside the discriminator network. The resulting architecture can be trained on unaligned image datasets while benefiting from the robustness and efficiency of perceptual losses. We demonstrate the merits of the new architecture in a series of qualitative and quantitative comparisons with baseline approaches and state-of-the-art frameworks for unaligned image translation.