中文
相关论文

相关论文: All Patches Matter, More Patches Better: Enhance A…

200 篇论文

The rapid development of generative AI has made AI-generated images increasingly realistic and high-resolution. Most AI-generated image detection architectures typically downsample images before inputting them into models, risking the loss…

计算机视觉与模式识别 · 计算机科学 2026-01-05 Lawrence Han

In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence. Additionally, inaccuracies in…

计算机视觉与模式识别 · 计算机科学 2014-03-17 Yongkang Wong , Shaokang Chen , Sandra Mau , Conrad Sanderson , Brian C. Lovell

Identifying AI-generated content is critical for the safe and ethical use of generative AI. Recent research has focused on developing detectors that generalize to unknown generators, with popular methods relying either on high-level…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Seoyeon Gye , Junwon Ko , Hyounguk Shon , Minchan Kwon , Junmo Kim

Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for many applications, these models also pose significant societal…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Qijie Xu , Can Wang , Jiawei Chen , Siwei Lyu , Defang Chen

Recent advances in generative models have highlighted the need for robust detectors capable of distinguishing real images from AI-generated images. While existing methods perform well on known generators, their performance often declines…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Kuo Shi , Jie Lu , Shanshan Ye , Guangquan Zhang , Zhen Fang

With recent generative models facilitating photo-realistic image synthesis, the proliferation of synthetic images has also engendered certain negative impacts on social platforms, thereby raising an urgent imperative to develop effective…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Ouxiang Li , Jiayin Cai , Yanbin Hao , Xiaolong Jiang , Yao Hu , Fuli Feng

The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Jaime Álvarez Urueña , David Camacho , Javier Huertas Tato

Image anomaly detection consists in detecting images or image portions that are visually different from the majority of the samples in a dataset. The task is of practical importance for various real-life applications like biomedical image…

计算机视觉与模式识别 · 计算机科学 2022-10-28 Axel De Nardin , Pankaj Mishra , Gian Luca Foresti , Claudio Piciarelli

In the era of AIGC, the fast development of visual content generation technologies, such as diffusion models, bring potential security risks to our society. Existing generated image detection methods suffer from performance drop when faced…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Zheling Meng , Bo Peng , Jing Dong , Tieniu Tan

Current camera image and signal processing pipelines (ISPs), including deep-trained versions, tend to apply a single filter that is uniformly applied to the entire image. This is despite the fact that most acquired camera images have…

计算机视觉与模式识别 · 计算机科学 2023-06-28 Chandrajit Bajaj , Yi Wang , Yunhao Yang

While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse in realistic, in-the-wild scenarios. In this work, we demonstrate that…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Yue Zhou , Xinan He , Kaiqing Lin , Bing Fan , Feng Ding , Bin Li

With the rapid development of deep generative models (such as Generative Adversarial Networks and Diffusion models), AI-synthesized images are now of such high quality that humans can hardly distinguish them from pristine ones. Although…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Yan Ju , Shan Jia , Jialing Cai , Haiying Guan , Siwei Lyu

In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the…

计算机视觉与模式识别 · 计算机科学 2020-08-21 Taesung Park , Alexei A. Efros , Richard Zhang , Jun-Yan Zhu

The rapid proliferation of AI-Generated Images (AIGIs) has introduced severe risks of misinformation, making AIGI detection a critical yet challenging task. While traditional detection paradigms mainly rely on low-level features, recent…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Chenyang Zhu , Maorong Wang , Jun Liu , Ching-Chun Chang , Isao Echizen

Distinguishing between real and AI-generated images, commonly referred to as 'image detection', presents a timely and significant challenge. Despite extensive research in the (semi-)supervised regime, zero-shot and few-shot solutions have…

计算机视觉与模式识别 · 计算机科学 2025-04-23 Jonathan Brokman , Amit Giloni , Omer Hofman , Roman Vainshtein , Hisashi Kojima , Guy Gilboa

The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image forgery detection systems. Existing methods, whether non-LLM-based or LLM-based, exhibit…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Qing Huang , Zhipei Xu , Xuanyu Zhang , Xiangyu Yu , Jian Zhang

One of the key challenges of detecting AI-generated images is spotting images that have been created by previously unseen generative models. We argue that the limited diversity of the training data is a major obstacle to addressing this…

计算机视觉与模式识别 · 计算机科学 2025-06-11 Jeongsoo Park , Andrew Owens

Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…

计算机视觉与模式识别 · 计算机科学 2021-04-01 Chong Xiang , Arjun Nitin Bhagoji , Vikash Sehwag , Prateek Mittal

Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manually collecting a new training dataset that contains adequate…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Shuyang Sun , Liang Chen , Gregory Slabaugh , Philip Torr

Generative models have shown a giant leap in synthesizing photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Zihan Liu , Hanyi Wang , Yaoyu Kang , Shilin Wang