all AI news
Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization
March 25, 2024, 4:45 a.m. | Jimyeong Kim, Jungwon Park, Wonjong Rhee
cs.CV updates on arXiv.org arxiv.org
Abstract: In text-to-image personalization, a timely and crucial challenge is the tendency of generated images overfitting to the biases present in the reference images. We initiate our study with a comprehensive categorization of the biases into background, nearby-object, tied-object, substance (in style re-contextualization), and pose biases. These biases manifest in the generated images due to their entanglement into the subject embedding. This undesired embedding entanglement not only results in the reflection of biases from the reference …
abstract arxiv biases challenge contextualization cs.cv embedding generated image images object overfitting personalization reduce reference study style text text-to-image type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Principal Machine Learning Engineer (AI, NLP, LLM, Generative AI)
@ Palo Alto Networks | Santa Clara, CA, United States
Consultant Senior Data Engineer F/H
@ Devoteam | Nantes, France