Cover Image

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Jeeyung, Esmaeili, Erfan, Qiu, Qiang
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
by: Kim, Jeeyung, et al.
Published: (2024)

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
by: Kim, Taehoon, et al.
Published: (2025)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
by: Kim, Eunji, et al.
Published: (2024)

Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation
by: Lin, Feng, et al.
Published: (2025)

BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation
by: Chakraborty, Rajatsubhra, et al.
Published: (2025)

Information Theoretic Text-to-Image Alignment
by: Wang, Chao, et al.
Published: (2024)

Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
by: Colombo, Antonio, et al.
Published: (2026)

Improving Long-Text Alignment for Text-to-Image Diffusion Models
by: Liu, Luping, et al.
Published: (2024)

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
by: Kim, Jinyeong, et al.
Published: (2025)

TempoControl: Temporal Attention Guidance for Text-to-Video Models
by: Schiber, Shira, et al.
Published: (2025)

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
by: Zhao, Kairan, et al.
Published: (2026)

Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
by: Zhang, Yunzhe, et al.
Published: (2026)

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation
by: Dahary, Omer, et al.
Published: (2024)

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization
by: Nam, Jisu, et al.
Published: (2024)

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
by: Kang, Wonjun, et al.
Published: (2025)

Aligning Text to Image in Diffusion Models is Easier Than You Think
by: Lee, Jaa-Yeon, et al.
Published: (2025)

RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment
by: Wang, Chao, et al.
Published: (2025)

Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
by: Izadi, Amir Mohammad, et al.
Published: (2025)

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
by: Lee, Byung Hyun, et al.
Published: (2025)

Expressive Text-to-Image Generation with Rich Text
by: Ge, Songwei, et al.
Published: (2023)

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
by: Yu, Lu, et al.
Published: (2024)

Semimage: HSV-Based Semantic Image Encoding for Disentangled Text Representation
by: Zare, Mohammad
Published: (2025)

TextCraftor: Your Text Encoder Can be Image Quality Controller
by: Li, Yanyu, et al.
Published: (2024)

Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models
by: Zhang, Yasi, et al.
Published: (2024)

TextCAM: Explaining Class Activation Map with Text
by: Zhao, Qiming, et al.
Published: (2025)

Model-Agnostic Human Preference Inversion in Diffusion Models
by: Kim, Jeeyung, et al.
Published: (2024)

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
by: Bahng, Hyojin, et al.
Published: (2025)

Contrast-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment
by: Lv, Song-Lin, et al.
Published: (2025)

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
by: Kim, Jaemin, et al.
Published: (2024)

Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models
by: Motamed, Saman, et al.
Published: (2024)

Improving GFlowNets for Text-to-Image Diffusion Alignment
by: Zhang, Dinghuai, et al.
Published: (2024)

Text-Guided Image Clustering
by: Stephan, Andreas, et al.
Published: (2024)

Hyperbolic Image-Text Representations
by: Desai, Karan, et al.
Published: (2023)

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
by: Lee, Jaa-Yeon, et al.
Published: (2026)

Controlling Text-to-Image Diffusion by Orthogonal Finetuning
by: Qiu, Zeju, et al.
Published: (2023)

Directional Textual Inversion for Personalized Text-to-Image Generation
by: Kim, Kunhee, et al.
Published: (2025)

ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
by: Xing, Eric, et al.
Published: (2025)

Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
by: Ganjdanesh, Alireza, et al.
Published: (2024)

All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
by: Li, Shuangqi, et al.
Published: (2024)

Learning to Rank Caption Chains for Video-Text Alignment
by: Blume, Ansel, et al.
Published: (2026)