中文
相关论文

相关论文: No Label Left Behind: A Unified Surface Defect Det…

200 篇论文

Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Shibo Yao , Renshuai Tao , Xiaolong Zheng , Chao Liang , Chunjie Zhang

Document layout analysis is a key area in document research, involving techniques like text mining and visual analysis. Despite various methods developed to tackle layout analysis, a critical but frequently overlooked problem is the…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Talha Uddin Sheikh , Tahira Shehzadi , Khurram Azeem Hashmi , Didier Stricker , Muhammad Zeshan Afzal

Visual anomaly detection (AD) for industrial inspection is a highly relevant task in modern production environments. The problem becomes particularly challenging when training and deployment data differ due to changes in acquisition…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Lukas Roming , Felix Lehnerer , Jonas V. Funk , Andreas Michel , Georg Maier , Thomas Längle , Jürgen Beyerer

Foundation models are currently driving a paradigm shift in computer vision tasks for various fields including biology, astronomy, and robotics among others, leveraging user-generated prompts to enhance their performance. In the Laser…

计算机视觉与模式识别 · 计算机科学 2024-06-27 Israt Zarin Era , Imtiaz Ahmed , Zhichao Liu , Srinjoy Das

Pixel-wise segmentation is one of the most data and annotation hungry tasks in our field. Providing representative and accurate annotations is often mission-critical especially for challenging medical applications. In this paper, we propose…

计算机视觉与模式识别 · 计算机科学 2021-04-28 Simon Reiß , Constantin Seibold , Alexander Freytag , Erik Rodner , Rainer Stiefelhagen

Detecting manipulated media has now become a pressing issue with the recent rise of deepfakes. Most existing approaches fail to generalize across diverse datasets and generation techniques. We thus propose a novel ensemble framework,…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Vrushank Ahire , Aniruddh Muley , Shivam Zample , Siddharth Verma , Pranav Menon , Surbhi Madan , Abhinav Dhall

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…

机器学习 · 计算机科学 2020-09-25 Wei-Hong Li , Chuan-Sheng Foo , Hakan Bilen

Small object detection is a broadly investigated research task and is commonly conceptualized as a "pipeline-style" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where…

计算机视觉与模式识别 · 计算机科学 2025-04-30 Siwei Wang , Zhiwei Chen , Liujuan Cao , Rongrong Ji

Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and…

图像与视频处理 · 电气工程与系统科学 2026-01-06 Zihan Li , Dandan Shan , Yunxiang Li , Paul E. Kinahan , Qingqi Hong

Industrial surface defect detection often suffers from limited defect samples, severe long-tailed distributions, and difficulties in accurately localizing subtle defects under complex backgrounds. To address these challenges, this paper…

人工智能 · 计算机科学 2026-04-22 Shuo Feng , Runlin Zhou , Yuyang Li , Guangcan Liu

Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers…

计算机视觉与模式识别 · 计算机科学 2022-03-18 Mingkai Zheng , Shan You , Lang Huang , Fei Wang , Chen Qian , Chang Xu

Automating the monitoring of industrial processes has the potential to enhance efficiency and optimize quality by promptly detecting abnormal events and thus facilitating timely interventions. Deep learning, with its capacity to discern…

In the context of flexible manufacturing systems that are required to produce different types and quantities of products with minimal reconfiguration, this paper addresses the problem of unsupervised multi-class anomaly detection: develop a…

计算机视觉与模式识别 · 计算机科学 2023-07-18 Haonan Yin , Guanlong Jiao , Qianhui Wu , Borje F. Karlsson , Biqing Huang , Chin Yew Lin

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

机器学习 · 计算机科学 2019-11-20 Qian Wang , Toby P. Breckon

Stripe-like space target detection (SSTD) plays a key role in enhancing space situational awareness and assessing spacecraft behaviour. This domain faces three challenges: the lack of publicly available datasets, interference from stray…

计算机视觉与模式识别 · 计算机科学 2024-09-17 Zijian Zhu , Ali Zia , Xuesong Li , Bingbing Dan , Yuebo Ma , Enhai Liu , Rujin Zhao

Supervised learning models often make systematic errors on rare subsets of the data. When these subsets correspond to explicit labels in the data (e.g., gender, race) such poor performance can be identified straightforwardly. This paper…

机器学习 · 计算机科学 2021-10-19 Greg d'Eon , Jason d'Eon , James R. Wright , Kevin Leyton-Brown

Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on…

计算机视觉与模式识别 · 计算机科学 2021-07-06 Poojan Oza , Vishwanath A. Sindagi , Vibashan VS , Vishal M. Patel

Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classification and segmentation tasks. However, the incorporation of…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Runnan Chen , Youquan Liu , Lingdong Kong , Nenglun Chen , Xinge Zhu , Yuexin Ma , Tongliang Liu , Wenping Wang

Estimating building footprint maps from geospatial data is of paramount importance in urban planning, development, disaster management, and various other applications. Deep learning methodologies have gained prominence in building…

计算机视觉与模式识别 · 计算机科学 2024-05-07 Anuja Vats , David Völgyes , Martijn Vermeer , Marius Pedersen , Kiran Raja , Daniele S. M. Fantin , Jacob Alexander Hay

Unsupervised validation of anomaly-detection models is a highly challenging task. While the common practices for model validation involve a labeled validation set, such validation sets cannot be constructed when the underlying datasets are…

机器学习 · 计算机科学 2025-01-06 Lihi Idan