Results 1 to 10 of about 31,762 (259)

Weakly Supervised Domain Detection [PDF]

Transactions of the Association for Computational Linguistics, 2019
In this paper we introduce domain detection as a new natural language processing task. We argue that the ability to detect textual segments that are domain-heavy (i.e., sentences or phrases that are representative of and provide evidence for a given domain) could enhance the robustness and portability of various text classification applications.
Xu, Yumo, Lapata, Mirella
openaire   +4 more sources

Weakly supervised machine learning

CAAI Transactions on Intelligence Technology, 2023
Abstract Supervised learning aims to build a function or model that seeks as many mappings as possible between the training data and outputs, where each training data will predict as a label to match its corresponding ground‐truth value. Although supervised learning has achieved great success in many tasks, sufficient data supervision
Zeyu Ren, Shuihua Wang, Yudong Zhang 0001   +2 more
openaire   +2 more sources

Weakly supervised foreground learning for weakly supervised localization and detection

Pattern Recognition, 2023
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised object localization~(WSOL) and detection~(WSOD), have recently received attention in the computer vision community.
Jianxin Wu, Chen-Lin Zhang, Yin Li
exaly   +3 more sources

Domain-agnostic weakly supervised surgical instrument segmentation. [PDF]

Sci Rep
Recent advancements in visual foundation models open new avenues in the field of surgical instrument segmentation in medical images. Segmentation foundation models provide high segmentation accuracy for objects of interest that are selected via prompts ...
Peter R, Pham DXV, Matten P, Wu E, Nienhaus J, Meissen F, Menten MJ, Tagliabue E, Mathis-Ullrich F.   +8 more
europepmc   +2 more sources

SPMF-Net: Weakly Supervised Building Segmentation by Combining Superpixel Pooling and Multi-Scale Feature Fusion

Remote Sensing, 2020
The lack of pixel-level labeling limits the practicality of deep learning-based building semantic segmentation. Weakly supervised semantic segmentation based on image-level labeling results in incomplete object regions and missing boundary information ...
, , Min Deng
exaly   +3 more sources

A weakly-supervised follicle segmentation method in ultrasound images. [PDF]

Sci Rep
Accurate follicle segmentation in ultrasound images is crucial for monitoring follicle development, a key factor in fertility treatments. However, obtaining pixel-level annotations for fully supervised instance segmentation is often impractical due to ...
Liu G, Huang W, Li Y, Zhang Q, Fu J, Tang H, Huang J, Zhang Z, Zhang L, Wang Y, Hu J.   +10 more
europepmc   +2 more sources

Interpretable weakly-supervised learning through kernel density matrices: A digital pathology use case. [PDF]

PLoS One
Classification methods based on deep learning require selecting between fully-supervised or weakly-supervised approaches, each presenting limitations in uncertainty quantification and interpretability.
Medina S, Romero E, Cruz-Roa A, González FA.   +3 more
europepmc   +2 more sources

Weakly Supervised Contrastive Learning [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance discrimination as the pretext task, which treating every single instance as a different class.
Mingkai Zheng, Fei Wang 0032, Shan You, Chen Qian 0006, Changshui Zhang, Xiaogang Wang 0001, Chang Xu 0002   +6 more
openaire   +2 more sources

Weakly supervised learning through box annotations for pig instance segmentation. [PDF]

Sci Rep
Pig instance segmentation is a critical component of smart pig farming, serving as the basis for advanced applications such as health monitoring and weight estimation.
Zhou H, Dong J, Han S, Chung S, Ali H, Kim S.   +5 more
europepmc   +2 more sources

Semi-Supervised Learning Matting Algorithm Based on Semantic Consistency of Trimaps

Applied Sciences, 2023
Image matting methods based on deep learning have made tremendous success. However, the success of previous image matting methods typically relies on a massive amount of pixel-level labeled data, which are time-consuming and costly to obtain.
Yating Kong, Jide Li, Liangpeng Hu, Xiaoqiang Li   +3 more
doaj   +1 more source