中文
相关论文

相关论文: Mind-the-Glitch: Visual Correspondence for Detecti…

200 篇论文

Medical image synthesis is crucial for alleviating data scarcity and privacy constraints. However, fine-tuning general text-to-image (T2I) models remains challenging, mainly due to the significant modality gap between complex visual details…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Xin Huang , Junjie Liang , Qingshan Hou , Peng Cao , Jinzhu Yang , Xiaoli Liu , Osmar R. Zaiane

Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is…

计算机视觉与模式识别 · 计算机科学 2023-02-02 Gihyun Kwon , Jong Chul Ye

Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos…

人工智能 · 计算机科学 2026-05-18 Eleonora Grassucci , Sergio Barbarossa , Danilo Comminiello

Evaluating identity preservation in generative models remains a critical yet unresolved challenge. Existing metrics rely on global embeddings or coarse VLM prompting, failing to capture fine-grained identity changes and providing limited…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Aditi Singhania , Krutik Malani , Riddhi Dhawan , Arushi Jain , Garv Tandon , Nippun Sharma , Souymodip Chakraborty , Vineet Batra , Ankit Phogat

Image-text matching (ITM) aims to address the fundamental challenge of aligning visual and textual modalities, which inherently differ in their representations, continuous, high-dimensional image features vs. discrete, structured text. We…

多媒体 · 计算机科学 2025-07-14 Junyu Chen , Yihua Gao , Mingyong Li

Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Le Zhang , Rabiul Awal , Aishwarya Agrawal

The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in generating contents that…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Yichen Sun , Zhixuan Chu , Zhan Qin , Kui Ren

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

计算机视觉与模式识别 · 计算机科学 2026-01-23 Theodoros Kouzelis , Efstathios Karypidis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…

计算与语言 · 计算机科学 2024-11-06 E. Zhixuan Zeng , Yuhao Chen , Alexander Wong

Deep metric learning applied to various applications has shown promising results in identification, retrieval and recognition. Existing methods often do not consider different granularity in visual similarity. However, in many domain…

计算机视觉与模式识别 · 计算机科学 2021-05-17 Dipu Manandhar , Muhammet Bastan , Kim-Hui Yap

Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the symbols. We propose a…

Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Existing approaches…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Huajie Jiang , Zhengxian Li , Xiaohan Yu , Yongli Hu , Baocai Yin , Jian Yang , Yuankai Qi

Establishing visual correspondence across images is a challenging and essential task. Recently, an influx of self-supervised methods have been proposed to better learn representations for visual correspondence. However, we find that these…

计算机视觉与模式识别 · 计算机科学 2022-07-25 Yingdong Hu , Renhao Wang , Kaifeng Zhang , Yang Gao

Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for…

In this paper, we investigate the semantic collapsing problem in generative personalization, an under-explored topic where the learned visual concept ($V$) gradually shifts from its original textual meaning and comes to dominate other…

机器学习 · 计算机科学 2026-02-26 Anh Bui , Trang Vu , Trung Le , Junae Kim , Tamas Abraham , Rollin Omari , Amar Kaur , Dinh Phung

Understanding how neural populations in higher visual areas encode object-centered visual information remains a central challenge in computational neuroscience. Prior works have investigated representational alignment between artificial…

神经元与认知 · 定量生物学 2026-03-12 Yule Wang , Joseph Yu , Chengrui Li , Weihan Li , Anqi Wu

We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…

计算机视觉与模式识别 · 计算机科学 2025-07-24 Ivona Najdenkoska , Animesh Sinha , Abhimanyu Dubey , Dhruv Mahajan , Vignesh Ramanathan , Filip Radenovic

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Zhiwei Yang , Pengfei Song , Yucong Meng , Kexue Fu , Shuo Wang , Zhijian Song

Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Yangyang Li , Daqing Liu , Wu Liu , Allen He , Xinchen Liu , Yongdong Zhang , Guoqing Jin

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Zeren Xiong , Yue Yu , Zedong Zhang , Shuo Chen , Jian Yang , Jun Li