Attribute Manipulation Generative Adversarial Networks for Fashion Images

By Kenan E. Ak, Ashraf Ali Kassim, Joo-Hwee Lim, Jo Yew Tham. 2019

85 citations recorded by the source corpus.

Recent advances in Generative Adversarial Networks (GANs) have made it possible to conduct multi-domain image-to-image translation using a single generative network. While recent methods such as Ganimation and SaGAN are able to conduct translations on attribute-relevant regions using attention, they do not perform well when the number of attributes increases as the training of attention masks mostly rely on classification losses. To address this and other limitations, we introduce Attribute Manipulation Generative Adversarial Networks (AMGAN) for fashion images. While AMGAN's generator network uses class activation maps (CAMs) to empower its attention mechanism, it also exploits perceptual losses by assigning reference (target) images based on attribute similarities. AMGAN incorporates an additional discriminator network that focuses on attribute-relevant regions to detect unrealistic translations. Additionally, AMGAN can be controlled to perform attribute manipulations on specific regions such as the sleeve or torso regions. Experiments show that AMGAN outperforms state-of-the-art methods using traditional evaluation metrics as well as an alternative one that is based on image retrieval.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Kun Zhou
2. Lawrence Carin
3. Haizhou Li
4. Rui Liu
5. Jianqiao Li
6. Sijia Wang
7. Yulai Cong
8. Berrak Sisman

Citations in the corpus

• GAN Memory with No Forgetting (2020, background): “Generative adversarial networks (GANs) GANs have shown increasing power to synthesize highly realistic observations [32, 45, 51, 9, 33, 34], and have found wide applicability in various fields [39, 1, 19, 81, 83, 84, 12, 89, 37].”
• Emotional Voice Conversion: Theory, Databases and ESD (2021, methodology): “To achieve this, translation models between the source and target domains have been studied, such as GANs [118, 119, 120, 121], CycleGANs [117], Augmented CycleGAN [122] and StarGAN [123] in computer vision problems.”
• On Leveraging Pretrained GANs for Limited-Data Generation (2020, methodology): “…Karras et al., 2019a); accordingly, GANs are widely applied to various research fields, such as image (Hoffman et al., 2017; Ledig et al., 2017; Ak et al., 2019), text (Lin et al., 2017; Fedus et al., 2018; Wang & Wan, 2018; Wang et al., 2019), video (Mathieu et al., 2015; Wang et al., 2017;…”
• On Leveraging Pretrained GANs for Generation with Limited Data (2020, methodology): “, 2019a;b); accordingly, they are widely applied in various research fields, such as image (Hoffman et al., 2017; Ledig et al., 2017; Ak et al., 2019), text (Lin et al.”