English
Related papers

Related papers: Deep Active Learning for Joint Classification & Se…

200 papers

Automatic lesion segmentation on thoracic CT enables rapid quantitative analysis of lung involvement in COVID-19 infections. However, obtaining a large amount of voxel-level annotations for training segmentation networks is prohibitively…

Image and Video Processing · Electrical Eng. & Systems 2021-11-22 Weiyi Xie , Colin Jacobs , Jean-Paul Charbonnier , Bram van Ginneken

Large annotated datasets are vital for training segmentation models, but pixel-level labeling is time-consuming, error-prone, and often requires scarce expert annotators, especially in medical imaging. In contrast, coarse annotations are…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Le Zhang , Fuping Wu , Arun Thirunavukarasu , Kevin Bronik , Thomas Nichols , Bartlomiej W. Papiez

Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements. Recently, active learning (AL) strategies strive to reduce annotation costs by querying a small…

Image and Video Processing · Electrical Eng. & Systems 2022-11-02 Ziyuan Zhao , Wenjing Lu , Zeng Zeng , Kaixin Xu , Bharadwaj Veeravalli , Cuntai Guan

Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…

Computer Vision and Pattern Recognition · Computer Science 2017-12-25 Lorenz Berger , Eoin Hyde , M. Jorge Cardoso , Sebastien Ourselin

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

Computer Vision and Pattern Recognition · Computer Science 2020-01-22 Clemens-Alexander Brust , Christoph Käding , Joachim Denzler

Active deep learning classification of hyperspectral images is considered in this paper. Deep learning has achieved success in many applications, but good-quality labeled samples are needed to construct a deep learning network. It is…

Machine Learning · Computer Science 2016-12-04 Peng Liu , Hui Zhang , Kie B. Eom

We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels which specify the object classes present in the image. Our method uses deep convolutional neural networks (CNNs) and…

Computer Vision and Pattern Recognition · Computer Science 2017-11-07 Qinbin Hou , Puneet Kumar Dokania , Daniela Massiceti , Yunchao Wei , Ming-Ming Cheng , Philip Torr

Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Qingdong Cai , Charith Abhayaratne

Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map corresponding to the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-20 Seunghan Yang , Yoonhyung Kim , Youngeun Kim , Changick Kim

When domain experts are needed to perform data annotation for complex machine-learning tasks, reducing annotation effort is crucial in order to cut down time and expenses. For cases when there are no annotations available, one approach is…

Machine Learning · Computer Science 2022-06-22 Einari Vaaras , Manu Airaksinen , Okko Räsänen

Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundation models or crowdsourced datasets are available, they are…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Hoyoung Kim , Sehyun Hwang , Suha Kwak , Jungseul Ok

Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…

Machine Learning · Computer Science 2024-08-26 Zongyao Lyu , William J. Beksi

Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Jort de Jong , Mike Holenderski

Semantic segmentation is crucial for various biomedical applications, yet its reliance on large annotated datasets presents a bottleneck due to the high cost and specialized expertise required for manual labeling. Active Learning (AL) aims…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Carsten T. Lüth , Jeremias Traub , Kim-Celine Kahl , Till J. Bungert , Lukas Klein , Lars Krämer , Paul F. Jaeger , Fabian Isensee , Klaus Maier-Hein

Deep Active Learning (DAL) has been advocated as a promising method to reduce labeling costs in supervised learning. However, existing evaluations of DAL methods are based on different settings, and their results are controversial. To…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Yu Li , Muxi Chen , Yannan Liu , Daojing He , Qiang Xu

Weakly supervised nuclei segmentation is a critical problem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost. Adopting point annotations, previous methods mostly rely on…

Image and Video Processing · Electrical Eng. & Systems 2022-02-14 Weizhen Liu , Qian He , Xuming He

The generalisation performance of a convolutional neural network (CNN) is influenced by the quantity, quality, and variety of the training images. Training images must be annotated, and this is time consuming and expensive. The goal of our…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Pieter M. Blok , Gert Kootstra , Hakim Elchaoui Elghor , Boubacar Diallo , Frits K. van Evert , Eldert J. van Henten

Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard classification models learned on such data distribution…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Chi Zhang , Guosheng Lin , Lvlong Lai , Henghui Ding , Qingyao Wu

Accurate instrument segmentation in endoscopic vision of robot-assisted surgery is challenging due to reflection on the instruments and frequent contacts with tissue. Deep neural networks (DNN) show competitive performance and are in favor…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Haonan Peng , Shan Lin , Daniel King , Yun-Hsuan Su , Randall A. Bly , Kris S. Moe , Blake Hannaford

We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting…

Computer Vision and Pattern Recognition · Computer Science 2018-08-17 Arslan Chaudhry , Puneet K. Dokania , Philip H. S. Torr