Active learning-based optimized training library generation for object-oriented image classification

R Balasubramaniam, S Namboodiri… - … and remote sensing, 2017 - ieeexplore.ieee.org
… 3 and 4, it can be visually verified that the four classes, ie, roads (cyan), … is aided by fuzzy
c-means (FCM) clustering. The FCM helps in forming the training set for the SVM to learn. …

Deep Active Learning for Computer-Aided Detection of Nasopharyngeal Carcinoma in MRI Images

X Zhao, G Han, H Li, Z Wei, M Yang - Proceedings of the 2023 9th …, 2023 - dl.acm.org
visually analyze the trainedactive learning is applied to the object detection task of
nasopharyngeal carcinoma MRI images, and good results are obtained under small labeled training

Sos! self-supervised learning over sets of handled objects in egocentric action recognition

V Escorcia, R Guerrero, X Zhu, B Martinez - European Conference on …, 2022 - Springer
… that our OIC, aided with our SOS pre-training, complements … to supervise the learning of
active object detection. Li et al. [… pre-training [17] in the domain of egocentric visual perception, …

Deep active learning for automatic mitotic cell detection on HEp-2 specimen medical images

A Anaam, MA Al-Antari, J Hussain, N Abdel Samee… - Diagnostics, 2023 - mdpi.com
… -2 computer-aided diagnosis (CAD) system. The automatic … The IIF HEp-2 protocol involves
several visual analysis steps at … the recent deep learning object detectors in various imaging …

Solar-powered deep learning-based recognition system of daily used objects and human faces for assistance of the visually impaired

B Calabrese, R Velázquez, C Del-Valle-Soto… - Energies, 2020 - mdpi.com
visually impaired (VI) people in finding daily used objects. Object detection and recognition
in a … Automatic object detection and identification for VI people requires a flexible, adaptable, …

A few-shot learning approach for database-free vision-based monitoring on construction sites

J Kim, S Chi - Automation in Construction, 2021 - Elsevier
… on construction object detection, … visually distinct instances (eg, left-hand side, front-view,
rear side). One recent study also reported that an active learning scheme is effective in training

An ensemble deep learning method with optimized weights for drone-based water rescue and surveillance

J Gasienica-Jozkowy, M Knapik… - … Computer-Aided …, 2021 - content.iospress.com
… The second contribution is our proposed object detection method. It is an ensemble … To
visually compare proposed ensemble model to individual models, we chose version #3, …

A frame-work assisting the visually impaired people: common object detection and pose estimation in surrounding environment

VH Le, H Vu, TT Nguyen - 2018 5th NAFOSTED conference on …, 2018 - ieeexplore.ieee.org
… In term of deploying the aided-system for the VIPs, … A good survey in [7] presents vision-based
techniques in object recognition assisting VIPs . The most closed our works are visual-…

Deep learning reader for visually impaired

J Ganesan, AT Azar, S Alsenan, NA Kamal, B Qureshi… - Electronics, 2022 - mdpi.com
… people with visual impairment; namely, mobility, object detection and recognition and navigation.
… CNN [50] can be defined as a kind of deep learning neural network that has aided the …

WMBAL: weighted minimum bounds for active learning

S Lu, J Zheng, Z Li, X Dai - Applied Intelligence, 2024 - Springer
… To apply our active learning framework effectively to object detection, we establish category
… 3 and 4 visually depict the essential aspects of the raw image and point cloud data, …