WE5.PA.7

A DEBIASING FRAMEWORK FOR ATTRIBUTE BINDING IN DIFFUSION-BASED TEXT-TO-IMAGE GENERATION

Yueheng Luo, Tianwei Cao, Beijing University of Posts and Telecommunications, China; Rui Wang, Ling Jin, Weidong Liu, Donghui Gao, China Mobile Research Institute, China; Kongming Liang, Zhanyu Ma, Beijing University of Posts and Telecommunications, China
Session:
WE5.PA: Machine Learning in Signal Processing 13 Poster
Track:
[ML] Machine Learning in Signal Processing
Location:
Poster Area A
Presentation Time:
Wed, 17 Sep, 16:30 - 18:00 Anchorage Time (UTC -8)
Session Chair:
Shan Du, UBC-O
Presentation
Discussion
Resources
No resources available.
Session WE5.PA
WE5.PA.1: Real-Time Semantic Video Communication with Temporally Consistent and Controllable Diffusion Models
Cem Eteke, Alexander Griessel, Wolfgang Kellerer, Eckehard Steinbach, Technical University of Munich, Germany
WE5.PA.2: TEACH ME SIGN: STEPWISE PROMPTING LLM FOR SIGN LANGUAGE PRODUCTION
Zhaoyi An, Rei Kawakami, Institute of Science Tokyo, Japan
WE5.PA.3: GMAR: GRADIENT-DRIVEN MULTI-HEAD ATTENTION ROLLOUT FOR VISION TRANSFORMER INTERPRETABILITY
Sehyeong Jo, Gangjae Jang, University of Colorado Boulder, Korea (South); Haesol Park, Korea Institute of Science and Technology, Korea (South)
WE5.PA.4: VISUAL PROMPTING THROUGH IMAGE MINES
Kalash Shah, Snehan J, Gautam Bhutani, Kunal Singh, Shreyas Singh, Fractal AI Research, India
WE5.PA.5: HARNESSING THE POWER OF LLMS FOR IMAGE AESTHETICS ASSESSMENT THROUGH SEMANTIC AND CONTEXTUAL UNDERSTANDING
Yoshia Abe, Tatsuya Daikoku, Yasuo Kuniyoshi, The University of Tokyo, Japan
WE5.PA.6: GMD: A MULTIMODAL FRAMEWORK FOR AI-GENERATED MISINFORMATION DETECTION
Junwen Duan, University of New South Wales, China; Wuyue Zhang, Zhende Liu, ZhejiangLab, China
WE5.PA.7: A DEBIASING FRAMEWORK FOR ATTRIBUTE BINDING IN DIFFUSION-BASED TEXT-TO-IMAGE GENERATION
Yueheng Luo, Tianwei Cao, Beijing University of Posts and Telecommunications, China; Rui Wang, Ling Jin, Weidong Liu, Donghui Gao, China Mobile Research Institute, China; Kongming Liang, Zhanyu Ma, Beijing University of Posts and Telecommunications, China
WE5.PA.8: SKETCH TO STYLIZED-IMAGE: A TWO-STAGE APPROACH FOR ARTISTIC IMAGE GENERATION
Jiyoon Kim, Junha Park, Jong-Seok Lee, Yonsei University, Korea (South)
WE5.PA.9: ASTROPHOTOGRAPHY TURBULENCE MITIGATION VIA GENERATIVE MODELS
Joonyeoup Kim, Yu Yuan, Xingguang Zhang, Xijun Wang, Stanley Chan, Purdue University, United States
WE5.PA.10: PIXELSHUFFLER: A SIMPLE IMAGE TRANSLATION THROUGH PIXEL REARRANGEMENT
Omar Zamzam, University of Southern California, United States
WE5.PA.11: Beta Wavelet Induced Multi-Scale Kernel Clustering: A Frequency-Aware Framework For Complex Data Analysis
Kerui Cheng, Yan Chen, Taiyuan University of Technology, China; Liang Du, Shanxi University, China
Contacts