English
Related papers

Related papers: Spectral Tail Auxiliary Learning for AI-Generated …

200 papers

Detection of rare lesions in whole-body CT is fundamentally limited by extreme class imbalance and low target-to-volume ratios, producing precision collapse despite high AUROC. Synthetic augmentation with diffusion models offers promise,…

Image and Video Processing · Electrical Eng. & Systems 2026-03-02 Yifan Li , Mehrdad Salimitari , Taiyu Zhang , Guang Li , David Dreizin

Hard coatings play a critical role in industry, with ceramic materials offering outstanding hardness and thermal stability for applications that demand superior mechanical performance. However, deploying artificial intelligence (AI) for…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Binwei Chen , Huachao Leng , Chi Yeung Mang , Tsz Wai Cheung , Yanhua Chen , Wai Keung Anthony Loh , Chi Ho Wong , Chak Yin Tang

Recent generative models show impressive performance in generating photographic images. Humans can hardly distinguish such incredibly realistic-looking AI-generated images from real ones. AI-generated images may lead to ubiquitous…

Computer Vision and Pattern Recognition · Computer Science 2024-03-08 Nan Zhong , Yiran Xu , Sheng Li , Zhenxing Qian , Xinpeng Zhang

Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Renan A. Rojas-Gomez , Karan Singhal , Ali Etemad , Alex Bijamov , Warren R. Morningstar , Philip Andrew Mansfield

Although the recent advancement in generative models brings diverse advantages to society, it can also be abused with malicious purposes, such as fraud, defamation, and fake news. To prevent such cases, vigorous research is conducted to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-08 Yonghyun Jeong , Doyeon Kim , Pyounggeon Kim , Youngmin Ro , Jongwon Choi

Scene Graph Generation (SGG) research has suffered from two fundamental challenges: the long-tailed predicate distribution and semantic ambiguity between predicates. These challenges lead to a bias towards head predicates in SGG models,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Kanghoon Yoon , Kibum Kim , Jaehyung Jeon , Yeonjun In , Donghyun Kim , Chanyoung Park

Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Prithvijit Chattopadhyay , Bharat Goyal , Boglarka Ecsedi , Viraj Prabhu , Judy Hoffman

Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Yanan Zhang , Chao Zhou , Di Huang

Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve…

Multimedia · Computer Science 2020-01-30 Amir Vatani , Milad Taleby Ahvanooey , Mostafa Rahimi

Recent generative models produce near-photorealistic images, challenging the trustworthiness of photographs. Synthetic image detection (SID) has thus become an important area of research. Prior work has highlighted how synthetic images…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Marco Willi , Melanie Mathys , Michael Graber

With the aim of detecting AI-generated images and identifying the specific models responsible for their generation, we propose a multi-modal multi-task model. The model leverages pre-trained BERT and CLIP Vision encoders for text and image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Xiaoyu Guo , Arkaitz Zubiaga

The rapid advances in generative AI models have empowered the creation of highly realistic images with arbitrary content, raising concerns about potential misuse and harm, such as Deepfakes. Current research focuses on training detectors…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Zhiyuan He , Pin-Yu Chen , Tsung-Yi Ho

As the success of Generative Adversarial Networks (GANs) on natural images quickly propels them into various real-life applications across different domains, it becomes more and more important to clearly understand their limitations.…

Machine Learning · Computer Science 2020-12-21 Mahyar Khayatkhoei , Ahmed Elgammal

Recent generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose, simply by learning from unlabeled image collections. Here, we investigate whether such views can be…

Computer Vision and Pattern Recognition · Computer Science 2021-04-30 Lucy Chai , Jun-Yan Zhu , Eli Shechtman , Phillip Isola , Richard Zhang

Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Na Dong , Yongqiang Zhang , Mingli Ding , Gim Hee Lee

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Chen-Long Duan , Yong Li , Xiu-Shen Wei , Lin Zhao

We present Soft Tail-dropping Adaptive Tokenizer (STAT), a 1D discrete visual tokenizer that adaptively chooses the number of output tokens per image according to its structural complexity and level of detail. STAT encodes an image into a…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Zeyuan Chen , Kai Zhang , Zhuowen Tu , Yuanjun Xiong

In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Ziyou Liang , Weifeng Liu , Run Wang , Mengjie Wu , Boheng Li , Yuyang Zhang , Lina Wang , Xinyi Yang

Pixel-wise predictions are required in a wide variety of tasks such as image restoration, image segmentation, or disparity estimation. Common models involve several stages of data resampling, in which the resolution of feature maps is first…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Shashank Agnihotri , Julia Grabinski , Margret Keuper

Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Gabriele Valvano , Antonino Agostino , Giovanni De Magistris , Antonino Graziano , Giacomo Veneri