English
Related papers

Related papers: Bridge the Gap: From Weak to Full Supervision for …

200 papers

Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Tianheng Cheng , Xinggang Wang , Shaoyu Chen , Qian Zhang , Wenyu Liu

Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 David Pujol-Perich , Albert Clapés , Sergio Escalera

Survival analysis stands as a pivotal process in cancer treatment research, crucial for predicting patient survival rates accurately. Recent advancements in data collection techniques have paved the way for enhancing survival predictions by…

Machine Learning · Computer Science 2024-07-26 Linhao Qu , Dan Huang , Shaoting Zhang , Xiaosong Wang

Image segmentation is one of the most essential biomedical image processing problems for different imaging modalities, including microscopy and X-ray in the Internet-of-Medical-Things (IoMT) domain. However, annotating biomedical images is…

Computer Vision and Pattern Recognition · Computer Science 2021-01-25 Ziyuan Zhao , Zeng Zeng , Kaixin Xu , Cen Chen , Cuntai Guan

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

Computation and Language · Computer Science 2022-05-10 Akim Tsvigun , Artem Shelmanov , Gleb Kuzmin , Leonid Sanochkin , Daniil Larionov , Gleb Gusev , Manvel Avetisian , Leonid Zhukov

Recently, deep self-training approaches emerged as a powerful solution to the unsupervised domain adaptation. The self-training scheme involves iterative processing of target data; it generates target pseudo labels and retrains the network.…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Inkyu Shin , Sanghyun Woo , Fei Pan , InSo Kweon

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Computer Vision and Pattern Recognition · Computer Science 2018-10-17 Zi-Yi Ke , Chiou-Ting Hsu

Recent advancements in industrial anomaly detection (AD) have demonstrated that incorporating a small number of anomalous samples during training can significantly enhance accuracy. However, this improvement often comes at the cost of…

Computer Vision and Pattern Recognition · Computer Science 2025-01-16 Hanxi Li , Jingqi Wu , Deyin Liu , Lin Wu , Hao Chen , Mingwen Wang , Chunhua Shen

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground…

Computer Vision and Pattern Recognition · Computer Science 2020-10-16 Zhedong Zheng , Yi Yang

Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Geuntaek Lim , Hyunwoo Kim , Joonsoo Kim , Yukyung Choi

Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM),…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Anurag Das , Anna Kukleva , Xinting Hu , Yuki M. Asano , Bernt Schiele

The growing demands of stroke rehabilitation have increased the need for solutions to support autonomous exercising. Virtual coaches can provide real-time exercise feedback from video data, helping patients improve motor function and keep…

Image and Video Processing · Electrical Eng. & Systems 2025-06-05 Gonçalo Mesquita , Ana Rita Cóias , Artur Dubrawski , Alexandre Bernardino

Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Yinghao Xu , Fangyun Wei , Xiao Sun , Ceyuan Yang , Yujun Shen , Bo Dai , Bolei Zhou , Stephen Lin

Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, limiting real-world scalability. Also, they focus on…

Sound · Computer Science 2025-07-28 Menglu Li , Xiao-Ping Zhang , Lian Zhao

While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect network calibration quality, resulting in misalignment between prediction confidence and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Wangkai Li , Rui Sun , Zhaoyang Li , Yujia Chen , Tianzhu Zhang

Accurate building damage assessment using bi-temporal multi-modal remote sensing images is essential for effective disaster response and recovery planning. This study proposes a novel Building-Guided Pseudo-Label Learning Framework to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Jiepan Li , He Huang , Yu Sheng , Yujun Guo , Wei He

Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence…

Computer Vision and Pattern Recognition · Computer Science 2023-10-23 Liyao Tang , Zhe Chen , Shanshan Zhao , Chaoyue Wang , Dacheng Tao

Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Bethany H. Thompson , Gaetano Di Caterina , Jeremy P. Voisey

Training a real-time gesture recognition model heavily relies on annotated data. However, manual data annotation is costly and demands substantial human effort. In order to address this challenge, we propose a framework that can…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Junxiao Shen , Xuhai Xu , Ran Tan , Amy Karlson , Evan Strasnick

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Hui Su , Yue Ye , Wei Hua , Lechao Cheng , Mingli Song