Open Access
Enhancing Deep Active Learning Using Selective Self-Training For Image Classification
Emmeleia Panagiota Mastoropoulou
- 01 Jan 2019
9
TL;DR: A high quality and large scale training data-set is an important guarantee to teach an ideal classifier for image classification.
read more
Abstract: A high quality and large scale training data-set is an important guarantee to teach an ideal classifier for image classification. Manually constructing a training data- set with appropriate labe ...
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
Uncertainty-aware Self-training for Few-shot Text Classification
Subhabrata Mukherjee,Ahmed Hassan Awadallah +1 more
- 01 Dec 2020
TL;DR: This work proposes an approach to improve self-training by incorporating uncertainty estimates of the underlying neural network leveraging recent advances in Bayesian deep learning and proposes acquisition functions to select instances from the unlabeled pool leveraging Monte Carlo (MC) Dropout and learning mechanism leveraging model confidence for self- training.
Meta Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang,Subhabrata Mukherjee,Haoda Chu,Yuancheng Tu,Ming Wu,Jing Gao,Ahmed Hassan Awadallah +6 more
- 14 Aug 2021
TL;DR: This paper proposed a meta self-training framework which leverages very few manually annotated labels for training neural sequence models, which helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
73
•Posted Content
Adaptive Self-training for Few-shot Neural Sequence Labeling.
Yaqing Wang,Subhabrata Mukherjee,Haoda Chu,Yuancheng Tu,Ming Wu,Jing Gao,Ahmed Hassan Awadallah +6 more
TL;DR: Self-training and meta-learning techniques for few-shot training of neural sequence taggers, namely MetaST are developed that help in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
57
GAN-BElectra: Enhanced Multi-class Sentiment Analysis with Limited Labeled Data
TL;DR: This paper proposed a novel sentiment analysis technique, named GAN-BElectra, which outperforms its baseline technique in terms of multiclass sentiment analysis accuracy with a few labeled data while maintaining an architecture with reduced complexity compared to its predecessor.
11
Towards Practical Active Learning for Classification
Y. Yang
- 20 Nov 2018
TL;DR: This thesis addresses the particular challenge of using as few annotations as possible, while at the same time, maintaining a good learning performance, and proposes two novel active learning methods that show a clear advantage over passive learning.
6
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
Reading Digits in Natural Images with Unsupervised Feature Learning
Yuval Netzer,Tao Wang,Adam Coates,Alessandro Bissacco,Bo Wu,Andrew Y. Ng +5 more
- 01 Jan 2011
TL;DR: A new benchmark dataset for research use is introduced containing over 600,000 labeled digits cropped from Street View images, and variants of two recently proposed unsupervised feature learning methods are employed, finding that they are convincingly superior on benchmarks.
Active Learning Literature Survey
Burr Settles
- 01 Jan 2009
TL;DR: This report provides a general introduction to active learning and a survey of the literature, including a discussion of the scenarios in which queries can be formulated, and an overview of the query strategy frameworks proposed in the literature to date.
6.7K
•Posted Content
Overcoming catastrophic forgetting in neural networks
James Kirkpatrick,Razvan Pascanu,Neil C. Rabinowitz,Joel Veness,Guillaume Desjardins,Andrei Rusu,Kieran Milan,John Quan,Tiago Ramalho,Agnieszka Grabska-Barwinska,Demis Hassabis,Claudia Clopath,Dharshan Kumaran,Raia Hadsell +13 more
TL;DR: It is shown that it is possible to overcome the limitation of connectionist models and train networks that can maintain expertise on tasks that they have not experienced for a long time and selectively slowing down learning on the weights important for previous tasks.
5K