most citedRS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2024

Dark Miner: Defend against undesirable generation for text-to-image diffusion models

Zheling Meng, Bo Peng, Xiaochuan Jin +4

Text-to-image diffusion models have been demonstrated with undesired generation due to unfiltered large-scale training data, such as sexual images and copyrights, necessitating the…

cs.CV2023★ 1 cited

RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models

Yue Jiang, Yueming Lyu, Tianxiang Ma +2

Recent text-conditioned image generation models have demonstrated an exceptional capacity to produce diverse and creative imagery with high visual quality. However, when pre-traine…

cs.CV2023

DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing

Yueming Lyu, Kang Zhao, Bo Peng +5

Text-guided image editing faces significant challenges when considering training and inference flexibility. Much literature collects large amounts of annotated image-text pairs to…

cs.CV2023

InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer

Yueming Lyu, Yue Jiang, Bo Peng +1

Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfe…

cs.CV2023

3D-Aware Adversarial Makeup Generation for Facial Privacy Protection

Yueming Lyu, Yue Jiang, Ziwen He +3

The privacy and security of face data on social media are facing unprecedented challenges as it is vulnerable to unauthorized access and identification. A common practice for solvi…