A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
[article]
2018
arXiv
pre-print
Preserved Fulltext
Other Versions
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any ...
This allows for an efficient implementation of curriculum learning on large-scale web images, resulting in a high-performance CNN model, where the negative impact of noisy labels is reduced substantially ...
Conclusion We have presented CurriculumNet -a new training strategy able to train CNN models more efficiently on large-scale weakly-supervised web images, where no human annotation is provided. ...
arXiv:1808.01097v4
fatcat:2wpmcqnemrehjo7chvlvpeosra
Weakly Supervised Learning with Side Information for Noisy Labeled Images
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we present an efficient weakly supervised learning by using a Side Information Network (SINet), which aims to effectively carry out a large scale classification with severely noisy labels ...
Besides, we released a fine-grained product dataset called AliProducts, which contains more than 2.5 million noisy web images crawled from the internet by using queries generated from 50,000 fine-grained ...
Particularly, we investigate the learning capability on large-scale web images without any human annotation.
Datasets. ...
arXiv:2008.11586v2
fatcat:336pp4msefeatjnt6bxd2k73ry
Suppressing Mislabeled Data via Grouping and Self-Attention
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. ...
The AFM has several appealing benefits for noise-robust deep learning. (i) It does not rely on any assumptions and extra clean subset. ...
Introduction In recent years, deep neural networks (DNNs) have achieved great success in various tasks, particularly in supervised learning tasks on large-scale image recognition challenges, such as ImageNet ...
arXiv:2010.15603v1
fatcat:zkm7py2bgjg45crdvl5dw7wzdq
Learning from Web Data with Self-Organizing Memory Module
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Learning from web data has attracted lots of research interest in recent years. ...
Particularly, we formulate our method under the framework of multi-instance learning by grouping ROIs (i.e., images and their region proposals) from the same category into bags. ...
Datasets Clothing1M: Clothing1M [54] is a large-scale fashion dataset designed for webly supervised learning. ...
arXiv:1906.12028v5
fatcat:75qvpao3jfcgljanwdrg5rallm
Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
2020
Proceedings of the 28th ACM International Conference on Multimedia
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2010.05864v1 fatcat:dgrigyhcxrc6pm37dlhwk7jqsy
Experiments on realistic webly supervised learning datasets Webvision-1000 and NUS-81-Web show the effectiveness and robustness of VSGraph-LC. ...
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. ...
INTRODUCTION Deep convolutional neural networks (CNNs) are successful by virtue of large-scale datasets with human annotation [23] . ...
doi:10.1145/3394171.3413952
dblp:conf/mm/YangCFYZZ20
fatcat:iithcxh27rbcvov4m7uqa4hv4u
Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
First, we establish the first benchmark of controlled real-world label noise from the web. This new benchmark enables us to study the web label noise in a controlled setting for the first time. ...
Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. ...
Curriculumnet: Weakly supervised learning from large-scale web images. In European Conference on Computer Vision (ECCV), 2018. ...
arXiv:1911.09781v3
fatcat:l2yhsf4oebcs3b7wkxl2uamcfu
When Do Curricula Work?
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2012.03107v2 fatcat:6fqqsqqzmrdphnplfqwuwnhncmOther Versions
We first investigate the implicit curricula resulting from architectural and optimization bias and find that samples are learned in a highly consistent order. ...
Inspired by common use cases of curriculum learning in practice, we investigate the role of limited training time budget and noisy data in the success of curriculum learning. ...
We appreciate the help with the experiments from Zachary Cain, Sam Ritchie, Ambrose Slone, and Vaibhav Singh. Lastly, XW would like to thank the team for all of the hospitality. ...
arXiv:2012.03107v3
fatcat:4ledippvgjbt7oaxhtnlvqp2ua
A Survey of Label-noise Representation Learning: Past, Present and Future
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.04406v1 fatcat:denuxdotoje73jma34cgugpmdm
We first clarify a formal definition for LNRL from the perspective of machine learning. ...
Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios. ...
As far as we know, LNRL is a special case of machine learning, which belongs to weakly supervised learning [44] . ...
arXiv:2011.04406v2
fatcat:76np6wyzvvag7ehy23cwyzdozm
Multi-label Iterated Learning for Image Classification with Label Ambiguity
[article]
2021
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. ...
Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are assigned a single label. ...
crawled from the web [50] . ...
doi:10.48550/arxiv.2111.12172
fatcat:3nqqsh3arjc6bbcodb54cx6yji
Exploiting Curriculum Learning in Unsupervised Neural Machine Translation
2021
Findings of the Association for Computational Linguistics: EMNLP 2021
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Curriculumnet: Weakly super-
Acknowledgements vised learning from large-scale web images. ...
To perform such fine-grained learning where x and y indicate sentences sampled from
from easy to difficult, we borrow the idea from self- monolingual dataset φl1 and φl2 . l1 and l2 ...
doi:10.18653/v1/2021.findings-emnlp.79
fatcat:jls247yfpfcnbocow7r6u4muvi