Filters








38,582 Hits in 3.9 sec

Detection and Localisation of Multiple In-Core Perturbations with Neutron Noise-Based Self-Supervised Domain Adaptation

Aiden Durrant, Georgios Leontidis, Stefanos Kollias, Luis Torres, Cristina Montalvo, Antonios Mylonakis, Christophe Demazière, Paolo Vinai
2021 Zenodo  
. • Derivation of core perturbation characteristics to classify and locate its origin. • Yet this is challenging due to the limited number of neutron detectors in western type reactors. • We ask, can we  ...  target input sample and processed simultaneously by the network.  ...  Kollias. "3D convolutional and recurrent neural networks for reactor perturbation unfolding and anomaly detection. " EPJ Nuclear Sciences & Technologies (2019).  ... 
doi:10.5281/zenodo.5575851 fatcat:nd45vlpcsnawzopfyn3hz44zji

Joint Symmetry Detection and Shape Matching for Non-Rigid Point Cloud [article]

Abhishek Sharma, Maks Ovsjanikov
2022 arXiv   pre-print
Despite the success of deep functional maps in non-rigid 3D shape matching, there exists no learning framework that models both self-symmetry and shape matching simultaneously.  ...  In this paper, we propose a novel framework that simultaneously learns both self symmetry as well as a pairwise map between a pair of shapes.  ...  Our work also follows a similar direction as we aim to learn shape matching and symmetry detection simultaneously.  ... 
arXiv:2112.02713v2 fatcat:riu4uphounh5fldmqfdrawowgq

Detection and localisation of multiple in-core perturbations with neutron noise-based self-supervised domain adaptation

A. Durrant
2021 Zenodo  
. • Derivation of core perturbation characteristics to classify and locate its origin. • Yet this is challenging due to the limited number of neutron detectors in western type reactors. • We ask, can we  ...  Data Acquisition • Real plant measurements are difficult to obtain, unlabelled, and anomalies are thankfully rare. • As such it is beneficial to have alternative means to train our algorithms. • Supervised  ...  • Importantly how can we make an arbitrary number of predictions per sample that change between samples?  ... 
doi:10.5281/zenodo.4438588 fatcat:deua6jo5dfccfkqbmrrid6fhj4

Who's that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images [article]

Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars
2016 arXiv   pre-print
To bridge this gap, we propose a graph-matching based self-labelling algorithm, which we coin HSL (Hungarian Self Labeling).  ...  In each series as well, there is considerable change in actor appearance due to makeup, lighting, ageing, etc.  ...  Active speakers detected by lip movement detection in video can then be labelled from the aligned subtitle and transcript files.  ... 
arXiv:1611.09162v1 fatcat:y2dhbx3rtzgtlev7nivio6vyji

Region Similarity Representation Learning [article]

Tete Xiao, Colorado J Reed, Xiaolong Wang, Kurt Keutzer, Trevor Darrell
2021 arXiv   pre-print
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation.  ...  Through object detection, instance segmentation, and dense pose estimation experiments, we illustrate how ReSim learns representations which significantly improve the localization and classification performance  ...  [6] where the authors observed that "linear classification accuracy is not monotonically related to transfer performance in detection."  ... 
arXiv:2103.12902v2 fatcat:x3j4gwqdbrbormhpw557t33ytu

Self-supervised Moving Vehicle Tracking with Stereo Sound [article]

Chuang Gan, Hang Zhao, Peihao Chen, David Cox, Antonio Torralba
2019 arXiv   pre-print
as a form of self-supervision, without resorting to the collection of ground-truth annotations.  ...  During training, knowledge embodied in a well-established visual vehicle detection model is transferred to the audio domain using unlabeled videos as a bridge.  ...  Cross-modal Self-supervised Learning Our work is in the domain of self-supervised learning, which exploits implicit labels that are freely available in the structure of the data.  ... 
arXiv:1910.11760v1 fatcat:4mkpm2bo75aerb6w5uampuzrrm

Generative and self-supervised domain adaptation for one-stage object detection

Kazuma Fujii, Kazuhiko Kawamoto
2021 Array  
Self-supervision-based methods [17, 18, 19 ] employ self-supervised tasks, such as reconstruction, image rotation prediction, and self-training.  ...  To take advantage of both the adversarial generative method and self-supervision-based method, we introduced a generative and self-supervised domain adaptation method.  ... 
doi:10.1016/j.array.2021.100071 fatcat:ovrgangnk5atjb7gms44walbka

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [article]

Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang
2022 arXiv   pre-print
STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.  ...  To mitigate the depth-shift, we introduce the geometry-aligned multi-scale training strategy to disentangle the camera parameters and guarantee the geometry consistency of domains.  ...  Before passing to the models, both the target and source domain input are further augmented by the GAMS strategy in Sec. 3.4, where images and camera intrinsic parameters are cautiously aligned via simultaneously  ... 
arXiv:2204.11590v2 fatcat:oho5oi4go5fxtavavfkqeoiqme

Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis [article]

Veronika Cheplygina, Marleen de Bruijne, Josien P. W. Pluim
2018 arXiv   pre-print
We review semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis/detection or segmentation tasks.  ...  We also discuss connections between these learning scenarios, and opportunities for future research.  ...  simultaneously.  ... 
arXiv:1804.06353v2 fatcat:xke66fsrgjanjmopwti5tze4fm

Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection [article]

Zongxian Li, Qixiang Ye, Chong Zhang, Jingjing Liu, Shijian Lu and Yonghong Tian
2020 arXiv   pre-print
In this work, we propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains while considering the instantaneous alignment  ...  Using multi-stage convolutional features, SGA is further aggregated to fully align hierarchical representations of detection models.  ...  In this study, we propose a Self-Guided Adaptation (SGA) model with a Self-Guided Progressive Sampling(SPS) strategy, and target at aligning feature representation and transferring detection models across  ... 
arXiv:2003.08777v2 fatcat:6xj52frxqrerrnx2lmtzh7cm2i

Track-based self-supervised classification of dynamic obstacles

Roman Katz, Juan Nieto, Eduardo Nebot, Bertrand Douillard
2010 Autonomous Robots  
This work introduces a self-supervised architecture for robust classification of moving obstacles in urban environments.  ...  Experiments show that the system is able to achieve 95% classification accuracy and to maintain the performance through on-line retraining when working conditions change.  ...  This work is supported by the Australian Research Council (ARC) Centre of Excellence program and the New South Wales Government.  ... 
doi:10.1007/s10514-010-9193-0 fatcat:aw57zqdtg5gsff5ovvxqtwa7ie

Unaligned Supervision For Automatic Music Transcription in The Wild [article]

Ben Maman, Amit H. Bermano
2022 arXiv   pre-print
We introduce NoteEM, a method for simultaneously training a transcriber and aligning the scores to their corresponding performances, in a fully-automated process.  ...  The scores are typically aligned using audio features and strenuous human intervention to generate training labels.  ...  Since accurate velocity information cannot be derived from separate-source midi, we believe self-supervision is the main direction for training velocity detection, and we leave this to future work.  ... 
arXiv:2204.13668v1 fatcat:bkqzv3iwb5cqxb6t673mvowamy

Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training [article]

Cheng Xue, Lequan Yu, Pengfei Chen, Qi Dou, Pheng-Ann Heng
2022 arXiv   pre-print
Notably, we further design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples in a self-supervised manner.  ...  Specifically, we employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples.  ...  Learning curve of global alignment loss. In Fig. 5 (c), we plot the change of global inter-sample relationship with and without the global alignment loss.  ... 
arXiv:2205.04723v1 fatcat:zmumvcntnzdtfbauvt7nba2cyy

Attention-Based Self-Supervised Feature Learning for Security Data [article]

I-Ta Lee, Manish Marwah, Martin Arlitt
2020 arXiv   pre-print
The learned features are used in an anomaly detection model and perform better than learned features from baseline methods.  ...  In this paper, we design a self-supervised sequence-to-sequence model with attention to learn an embedding for data routinely used in cyber-security applications.  ...  Conclusions We explored multiple methods for unsupervised and self-supervised feature learning for security data.  ... 
arXiv:2003.10639v1 fatcat:lqkqpfqj6bbknpxgwci7bifrdu

COMPUTATIONAL ANALYSIS ON GENE EXPRESSION PATTERN: A SURVEY

K Vimala, D Usha
2018 International Journal of Advanced Research  
Sequence analysis and alignment 11  ...  As part of the chromosome, the sub-functions are self-learned or self-evolved.  ... 
doi:10.21474/ijar01/7270 fatcat:n73sxl6hurernpjbdp54aau4pq
« Previous Showing results 1 — 15 out of 38,582 results