检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xiong, Zhen Li, Yuqi Yang, Chuanguang Tan, Tiao Zhu, Zhihong Li, Siyuan Ma, Yue Institute of Computing Technology Chinese Academy of Sciences China Tsinghua University China Peking University China EaseUS China The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798350368741

Diffusion transformer (DiT) architecture catches much attention in image generation, which achieves better fidelity, performance, and diversity. However, most existing DiT-based image generation methods are global-aware synthesis and regional prompt control is less explored. In this paper, we propose a coarse-to-fine generation pipeline for regional prompt-following generation. Specifically, we first leverage the powerful large language model (LLM) to generate the high-level description of image (such as content, topic, and objects) and low-level description of image (such as details and style). Then we explore the influence of cross-attention layers in different depths. We discover that deeper layers always responsible for the high-level content control, while the shallow layers handles low-level content control. The various prompts are injected into the proposed regional cross-attention control in order for course-to-fine generation. Using the proposed pipeline, we improve the controllability of DiT-based image generation. Extensive quantitative and qualitative results demonstrate that our pipeline enables to improve the generated performance. Our codes are available at https://***/ZhenXiong-dl/ICASSP2025-RCAC. © 2025 IEEE.

关键词： Diffusion model Diffusion transformer text-to-image generation

来源：评论

学校读者我要写书评

暂无评论

AI-driven design exploration: Utilizing brand logos as an inspiration source for architectural design

引用

AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING 2025年 39卷 e5-e5页

作者： Celik, Tugce Ergin, Elif Akagun Ostim Tech Univ Ankara Turkiye

This study is predicated on the limited scholarly exploration of the connection between logos and the architectural spaces associated with these brands. The primary objective of this paper is to investigate the relationship between a brand's corporate identity and its architectural structures through a holistic approach, leveraging artificial intelligence (AI) as a design tool. To achieve this, this study conducts an interdisciplinary literature review, synthesizing existing works in both architecture and branding. The research methodology follows a qualitative, exploratory framework, focusing on the formal and aesthetic evaluations of AI-driven visual outputs. In this context, the central aim of this study is to explore the use of contemporary technologies as a design instrument within the architectural domain. Another key objective is to examine the application of AI as a methodological tool for architectural design within the context of corporate identity. To this end, architectural forms were visually generated using text-to-image and image-to-image, with the resulting products assessed in terms of architectural presentation techniques, visual quality, and aesthetic strategies. For the study's empirical component, brands ranked at the top of the 2023 Best Global Brands report were selected as the sample, and AI-driven architectural productions were created based on their logos. The findings suggest that AI, with its diverse styles and capabilities, can serve as a design parameter within architectural practice. This study contributes to the discourse on the evolving intersection of AI, branding, and architectural design, proposing new perspectives on the integration of these domains in the design process.

关键词： architectural design corporate identity brand architecture text-to-image generation human-computer interaction

来源：评论

学校读者我要写书评

暂无评论

Revealing Gender Bias from Prompt to image in Stable Diffusion

引用

JOURNAL OF IMAGING 2025年第2期11卷 35-35页

作者： Wu, Yankun Nakashima, Yuta Garcia, Noa Osaka Univ Ctr D3 Suita Osaka 5650871 Japan

Social biases in generative models have gained increasing attention. This paper proposes an automatic evaluation protocol for text-to-image generation, examining how gender bias originates and perpetuates in the generation process of Stable Diffusion. Using triplet prompts that vary by gender indicators, we trace presentations at several stages of the generation process and explore dependencies between prompts and images. Our findings reveal the bias persists throughout all internal stages of the generating process and manifests in the entire images. For instance, differences in object presence, such as different instruments and outfit preferences, are observed across genders and extend to overall image layouts. Moreover, our experiments demonstrate that neutral prompts tend to produce images more closely aligned with those from masculine prompts than with their female counterparts. We also investigate prompt-image dependencies to further understand how bias is embedded in the generated content. Finally, we offer recommendations for developers and users to mitigate this effect in text-to-image generation.

关键词： gender bias bias evaluation text-to-image generation

来源：评论

学校读者我要写书评

暂无评论

text-Guided Synthesis in Medical Multimedia Retrieval: A Framework for Enhanced Colonoscopy image Classification and Segmentation

引用

ALGORITHMS 2025年第3期18卷 155-155页

作者： Peter, Ojonugwa Oluwaf Ejiga emi Adeniran, Opeyemi Taiwo John-Otumu, Adetokunbo MacGregor Khalifa, Fahmi Rahman, Md Mahmudur Morgan State Univ Sch Comp Math & Nat Sci Dept Comp Sci Baltimore MD 21251 USA Morgan State Univ Dept Elect & Comp Engn Baltimore MD 21251 USA Fed Univ Technol Owerri Dept Informat Technol Owerri 460116 Imo Nigeria

The lack of extensive, varied, and thoroughly annotated datasets impedes the advancement of artificial intelligence (AI) for medical applications, especially colorectal cancer detection. Models trained with limited diversity often display biases, especially when utilized on disadvantaged groups. Generative models (e.g., DALL-E 2, Vector-Quantized Generative Adversarial Network (VQ-GAN)) have been used to generate images but not colonoscopy data for intelligent data augmentation. This study developed an effective method for producing synthetic colonoscopy image data, which can be used to train advanced medical diagnostic models for robust colorectal cancer detection and treatment. text-to-image synthesis was performed using fine-tuned Visual Large Language Models (LLMs). Stable Diffusion and DreamBooth Low-Rank Adaptation produce images that look authentic, with an average Inception score of 2.36 across three datasets. The validation accuracy of various classification models Big Transfer (BiT), Fixed Resolution Residual Next generation Network (FixResNeXt), and Efficient Neural Network (EfficientNet) were 92%, 91%, and 86%, respectively. Vision Transformer (ViT) and Data-Efficient image Transformers (DeiT) had an accuracy rate of 93%. Secondly, for the segmentation of polyps, the ground truth masks are generated using Segment Anything Model (SAM). Then, five segmentation models (U-Net, Pyramid Scene Parsing Network (PSNet), Feature Pyramid Network (FPN), Link Network (LinkNet), and Multi-scale Attention Network (MANet)) were adopted. FPN produced excellent results, with an Intersection Over Union (IoU) of 0.64, an F1 score of 0.78, a recall of 0.75, and a Dice coefficient of 0.77. This demonstrates strong performance in terms of both segmentation accuracy and overlap metrics, with particularly robust results in balanced detection capability as shown by the high F1 score and Dice coefficient. This highlights how AI-generated medical images can improve colonoscopy anal

关键词： medical imaging synthesis polyp detection text-to-image generation image segmentation generative AI medical image synthesis colorectal cancer detection data augmentation synthetic colonoscopy images DreamBooth Stable Diffusion Low-Rank Adaptation (LoRA) polyp segmentation Feature Pyramid Network Vision Transformer Segment Anything Model medical diagnostic models healthcare AI

来源：评论

学校读者我要写书评

暂无评论

A new frontier in design studio: AI and human collaboration in conceptual design

引用

Frontiers of Architectural Research 2025年

作者： Karadağ, Derya Ozar, Betül Faculty of Arts Design and Architecture Işık University Istanbul Turkey

This study explores the role of artificial intelligence (AI) in the conceptual design phase of interior design education, focusing on AI's potential to help students visualise and refine creative ideas. Conducted within a design studio course, the research integrates text-to-image generators, particularly Midjourney to support students' design processes. Implemented in the fourth week of a 14-week course, a structured workshop introduced students to Midjourney, with surveys conducted both at this stage and during the final submission to capture changes in student perspectives. Using a two-phase case study involving a workshop, surveys, and interviews among senior undergraduate students in the bachelor's program of the Interior Architecture and Environmental Design Department, the study assesses the impact of AI prompts, from simple keywords to detailed narratives, on concept development and project outcomes. Findings indicate that AI broadens design possibilities, facilitates iterative ideation, and improves conceptual precision through high-fidelity visualizations. While students view AI as a valuable addition to their creative process, they also express concerns about ethics and the need to balance AI's benefits with preserving design authenticity. This research contributes to the broader discussion on AI's role in design, advocating for a balanced integration that respects both technological potential and human creativity. © 2025 The Author(s)

关键词： Artificial intelligence Conceptual development Design process Interior design education text-to-image generation

来源：评论

学校读者我要写书评

暂无评论

Multimodal Intelligence: Representation Learning, Information Fusion, and Applications

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2020年第3期14卷 478-493页

作者： Zhang, Chao Yang, Zichao He, Xiaodong Deng, Li Univ Cambridge Dept Engn Cambridge CB2 1PZ England JD Com Inc JD AI Res Beijing 100101 Peoples R China Citadel LLC Chicago IL 60603 USA Citadel Amer Seattle WA 98121 USA

Deep learning methods haverevolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial intelligence field involve multiple modalities. Therefore, it is of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, we provide a technical review of available models and learning methods for multimodal intelligence. The main focus of this review is the combination of vision and natural language modalities, which has become an important topic in both the computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications. Regarding multimodal representation learning, we review the key concepts of embedding, which unify multimodal signals into a single vector space and thereby enable cross-modality signal processing. We also review the properties of many types of embeddings that are constructed and learned for general downstream tasks. Regarding multimodal fusion, this review focuses on special architectures for the integration of representations of unimodal signals for a particular task. Regarding applications, selected areas of a broad interest in the current literature are covered, including image-to-text caption generation, text-to-image generation, and visual question answering. We believe that this review will facilitate future studies in the emerging field of multimodal intelligence for related communities.

关键词： Task analysis Visualization Machine learning Training Semantics Natural language processing Multimodality representation multimodal fusion deep learning embedding speech vision natural language caption generation text-to-image generation visual question answering visual reasoning

来源：评论

学校读者我要写书评

暂无评论

Attentional Generative Adversarial Networks With Representativeness and Diversity for Generating text to Realistic image

引用

IEEE ACCESS 2020年 8卷 9587-9596页

作者： Tian, Anjie Lu, Lu South China Univ Technol Sch Comp Sci & Engn Guangzhou 510000 Peoples R China

In recent years, with the emergence and rapid development of Generative Adversarial Networks (GANs), the generation of realistic images consistent with their semantics based on text description has become one of the most popular research directions in the field of computer vision. Although the idea of applying attention mechanism has been raised out in many implementation methods, it is required to treat the sub-regions of the generated images equally. For this reason, this paper proposes a novel generative adversarial networks, rdAttnGAN, which generate text to fine images by training multi-pair generators and discriminators. Comparing with the conventional models, it pays more attention to the representativeness and diversity of the generated images. In addition, an optimization method for calculating the similarity between the generated image and the text description is also introduced to enhance the representative judgment of the images. By paying more attention to the generation of important sub-regions of images, the model can further optimize the training of generators. In order to verify the effectiveness of our proposed framework, a comprehensive set of experiments are conducted on CUB dataset and COCO dataset. The results demonstrate viability to improve the representativeness and diversity of images with our rdAttnGAN.

关键词： GANs representativeness and diversity text-to-image generation

来源：评论

学校读者我要写书评

暂无评论

image manipulation with natural language using Two-sided Attentive Conditional Generative Adversarial Network

引用

NEURAL NETWORKS 2021年 136卷 207-217页

作者： Zhu, Dawei Mogadala, Aditya Klakow, Dietrich Saarland Univ Spoken Language Syst LSV Saarland Informat Campus Saarbrucken Germany

Altering the content of an image with photo editing tools is a tedious task for an inexperienced user, especially, when modifying the visual attributes of a specific object in an image without affecting other constituents such as background etc. To simplify the process of image manipulation and to provide more control to users, it is better to utilize a simpler interface like natural language. It also enables to semantically modify parts of an image according to the given text. Therefore, in this paper, we address the challenge of manipulating images using natural language descriptions. We propose the Two-sidEd Attentive conditional Generative Adversarial Network (TEA-cGAN) to generate semantically manipulated images. TEA-cGAN's contribution is seen as two-fold. The first contribution aims to attend locations that need to be modified during generation. It introduces two types of architectures that provide fine-grained attention both in the generator and discriminator of Generative Adversarial Network (GAN). To be specific, the first one i.e., the Single-scale architecture used in the generator focuses to modify only the text-relevant regions in an image and leaves other regions untouched. While the second one i.e., Multi-scale architecture further extended this idea by taking the different scales of image features into account. The second contribution purpose is to generate higher resolution images (e.g., 256 x 256) as they provide better quality and stability. Quantitative and qualitative experiments conducted on CUB and Oxford-102 datasets confirm that TEA-cGAN different scale architectures outperform existing methods while generating 128 x 128 resolution images including generating higher resolution image i.e., 256 x 256. (c) 2020 Elsevier Ltd. All rights reserved.

关键词： Generative Adversarial Network (GAN) text-to-image generation image manipulation

来源：评论

学校读者我要写书评

暂无评论

Enhancing fine-detail image synthesis from text descriptions by text aggregation and connection fusion module

引用

SIGNAL PROCESSING-image COMMUNICATION 2024年 122卷

作者： Zhou, Huaping Wu, Tao Ye, Senmao Qin, Xinru Sun, Kelei Anhui Univ Sci & Technol Sch Comp Sci & Engn Huainan 232001 Peoples R China South China Univ Technol Guangzhou 510641 Peoples R China

Synthesizing images with fine details from text descriptions is a challenge. The existing single-stage generative adversarial networks (GANs) fuse sentence features into the image generation process through affine transformation, which alleviate the problems of missing details and large computation from stacked networks. However, existing single-stage networks ignore the word features in the text description, resulting in a lack of detail in the generated image. To address this issue, we proposed a text aggregation module (TAM) to fuse sentence features and word features in a text by a simple spatial attention mechanism. Then we built a text connection fusion (TCF) block consisting mainly of gated recurrent unit (GRU) and up-sampled block. It can connect text features used in the up-sampled blocks to improve text utilization. Besides, to further improve the semantic consistency between text and the generated images, we introduce the deep attentional multimodal similarity model (DAMSM) loss, which monitors the similarity between text and improves semantic consistency. Experimental results prove that our method is superior to the state-of-the-art models on the CUB and COCO datasets, regarding both image fidelity and semantic consistency with the text.

关键词： Generative adversarial network Semantic consistency Spatial attention text-to-image generation Single-stage network

来源：评论

学校读者我要写书评

暂无评论

KT-GAN: Knowledge-Transfer Generative Adversarial Network for text-to-image Synthesis

引用

IEEE TRANSACTIONS ON image PROCESSING 2021年 30卷 1275-1290页

作者： Tan, Hongchen Liu, Xiuping Liu, Meng Yin, Baocai Li, Xin Dalian Univ Technol Sch Math Sci Dalian 116024 Peoples R China Shandong Jianzhu Univ Sch Comp Sci & Technol Jinan 250101 Peoples R China Dalian Univ Technol Dept Elect Informat & Elect Engn Dalian 116024 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Louisiana State Univ Sch Elect Engn & Comp Sci Baton Rouge LA 70803 USA Louisiana State Univ Ctr Computat & Technol Baton Rouge LA 70803 USA

This paper presents a new framework, Knowledge-Transfer Generative Adversarial Network (KT-GAN), for fine-grained text-to-image generation. We introduce two novel mechanisms: an Alternate Attention-Transfer Mechanism (AATM) and a Semantic Distillation Mechanism (SDM), to help generator better bridge the cross-domain gap between text and image. The AATM updates word attention weights and attention weights of image sub-regions alternately, to progressively highlight important word information and enrich details of synthesized images. The SDM uses the image encoder trained in the image-to-image task to guide training of the text encoder in the text-to-image task, for generating better text features and higher-quality images. With extensive experimental validation on two public datasets, our KT-GAN outperforms the baseline method significantly, and also achieves the competive results over different evaluation metrics.

关键词： Task analysis Semantics Generators Generative adversarial networks Knowledge engineering Feature extraction image generation Generative adversarial network knowledge distillation text-to-image generation alternate attention-transfer mechanism

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：