Cover Image

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Jungwon, Ko, Jungmin, Byun, Dongnam, Suh, Jangwon, Rhee, Wonjong
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Selective Aggregation of Attention Maps Improves Diffusion-Based Visual Interpretation
by: Park, Jungwon, et al.
Published: (2026)

DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation
by: Byun, Dongnam, et al.
Published: (2025)

Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation
by: Ko, Jungmin, et al.
Published: (2026)

Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization
by: Kim, Jimyeong, et al.
Published: (2024)

ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
by: Kim, Jimyeong, et al.
Published: (2025)

Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering
by: Choi, Changin, et al.
Published: (2025)

Evaluating Feature Attribution Methods for Electrocardiogram
by: Suh, Jangwon, et al.
Published: (2022)

Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing
by: Kim, Jaeill, et al.
Published: (2024)

Task-Specific Preconditioner for Cross-Domain Few-Shot Learning
by: Kang, Suhyun, et al.
Published: (2024)

Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization
by: Song, Yeji, et al.
Published: (2024)

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
by: Park, Jungwon, et al.
Published: (2026)

On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations
by: Jung, Euna, et al.
Published: (2024)

An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM
by: Kim, Wonkyun, et al.
Published: (2024)

Soft Head Selection for Injecting ICL-Derived Task Embeddings
by: Park, Jungwon, et al.
Published: (2025)

Towards a Better Evaluation of Out-of-Domain Generalization
by: Hwang, Duhun, et al.
Published: (2024)

Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness
by: Kim, Jaeill, et al.
Published: (2024)

Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification
by: Gao, Yunhe, et al.
Published: (2024)

Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
by: Rahman, Tanzila, et al.
Published: (2024)

Unveiling Key Aspects of Fine-Tuning in Sentence Embeddings: A Representation Rank Analysis
by: Jung, Euna, et al.
Published: (2024)

TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images
by: Koltsov, Kirill, et al.
Published: (2026)

Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching
by: Chen, Wenjing
Published: (2024)

Instance-Aligned Captions for Explainable Video Anomaly Detection
by: Song, Inpyo, et al.
Published: (2026)

NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior
by: Park, Dongwoo, et al.
Published: (2025)

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
by: Fu, Minghao, et al.
Published: (2025)

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
by: Jiang, Dongzhi, et al.
Published: (2024)

Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?
by: Liang, Susan, et al.
Published: (2026)

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
by: Liu, Yexin, et al.
Published: (2025)

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

Exploiting Text-Image Latent Spaces for the Description of Visual Concepts
by: Schmalwasser, Laines, et al.
Published: (2024)

GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?
by: Li, Ruihang, et al.
Published: (2026)

Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation
by: Wu, Xun, et al.
Published: (2024)

CA-LoRA: Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
by: Park, Minho, et al.
Published: (2025)

Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data
by: Zhang, Lei, et al.
Published: (2023)

DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy
by: Song, Jaewoo, et al.
Published: (2025)

AttenCraft: Attention-guided Disentanglement of Multiple Concepts for Text-to-Image Customization
by: Shentu, Junjie, et al.
Published: (2024)

PAFormer: Part Aware Transformer for Person Re-identification
by: Jung, Hyeono, et al.
Published: (2024)

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
by: Pang, Lianyu, et al.
Published: (2024)

Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera
by: Song, Inpyo, et al.
Published: (2024)

Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation
by: Tai, Ying, et al.
Published: (2025)

Personalized Residuals for Concept-Driven Text-to-Image Generation
by: Ham, Cusuh, et al.
Published: (2024)