Active learning combining uncertainty and diversity for multi‐class image classification

Gu, Yanfeng; Chiu, Steve C.

doi:10.1049/iet-cvi.2014.0140

Cited by 29 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Choosing samples according to their diversity means that added samples are dissimilar from those already implemented in the training dataset. Here we distinguish between Euclidean distance-based diversity (EBD), angle-based diversity (ABD), and cluster-based diversity (CBD) [81][82][83].…”

Section: Diversity Criteria Methodsmentioning

confidence: 99%

A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data

et al. 2021

View full text Add to dashboard Cite

The current exponential increase of spatiotemporally explicit data streams from satellite-based Earth observation missions offers promising opportunities for global vegetation monitoring. Intelligent sampling through active learning (AL) heuristics provides a pathway for fast inference of essential vegetation variables by means of hybrid retrieval approaches, i.e., machine learning regression algorithms trained by radiative transfer model (RTM) simulations. In this study we summarize AL theory and perform a brief systematic literature survey about AL heuristics used in the context of Earth observation regression problems over terrestrial targets. Across all relevant studies it appeared that: (i) retrieval accuracy of AL-optimized training data sets outperformed models trained over large randomly sampled data sets, and (ii) Euclidean distance-based (EBD) diversity method tends to be the most efficient AL technique in terms of accuracy and computational demand. Additionally, a case study is presented based on experimental data employing both uncertainty and diversity AL criteria. Hereby, a a simulated training data base by the PROSAIL-PRO canopy RTM is used to demonstrate the benefit of AL techniques for the estimation of total leaf carotenoid content (Cxc) and leaf water content (Cw). Gaussian process regression (GPR) was incorporated to minimize and optimize the training data set with AL. Training the GPR algorithm on optimally AL-based sampled data sets led to improved variable retrievals compared to training on full data pools, which is further demonstrated on a mapping example. From these findings we can recommend the use of AL-based sub-sampling procedures to select the most informative samples out of large training data pools. This will not only optimize regression accuracy due to exclusion of redundant information, but also speed up processing time and reduce final model size of kernel-based machine learning regression algorithms, such as GPR. With this study we want to encourage further testing and implementation of AL sampling methods for hybrid retrieval workflows. AL can contribute to the solution of regression problems within the framework of operational vegetation monitoring using satellite imaging spectroscopy data, and may strongly facilitate data processing for cloud-computing platforms.

show abstract

Section: Diversity Criteria Methodsmentioning

confidence: 99%

A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The selected criterion algorithms can rank the samples according to the uncertainty of a sample or its diversity [15]. These criteria are sometimes used together within classification problems [20], and are here applied separately to regression. The separate use of these criteria in this study already provides benefits, although it is possible to combine them as in classification problems.…”

Section: Active Learning Theorymentioning

confidence: 99%

Active Learning Methods for Efficient Hybrid Biophysical Variable Retrieval

Verrelst

Dethier

Rivera

et al. 2016

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Kernel-based machine learning regression algorithms (MLRAs) are potentially powerful methods for being implemented into operational biophysical variable retrieval schemes. However, they face difficulties in coping with large training data sets. With the increasing amount of optical remote sensing data made available for analysis and the possibility of using a large amount of simulated data from radiative transfer models (RTMs) to train kernel MLRAs, efficient data reduction techniques will need to be implemented. Active learning (AL) methods enable to select the most informative samples in a data set. This letter introduces six AL methods for achieving optimized biophysical variable estimation with a manageable training data set, and their implementation into a Matlab-based MLRA toolbox for semiautomatic use. The AL methods were analyzed on their efficiency of improving the estimation accuracy of the leaf area index and chlorophyll content based on PROSAIL simulations. Each of the implemented methods outperformed random sampling, improving retrieval accuracy with lower sampling rates. Practically, AL methods open opportunities to feed advanced MLRAs with RTM-generated training data for the development of operational retrieval models.Index Terms-Active learning (AL), hybrid retrieval methods, kernel methods, machine learning regression algorithms (MLRAs), PROSAIL, Sentinel-3.

show abstract

“…Shen et al (2004) define three broad criteria for determining which data will be most informative to the model if annotated: uncertainty, where instances which confuse the model are given priority; diversity, where instances that would expand the model's coverage are prioritized; and representativeness, prioritizing instances that best approximate the true distribution over all instances. Uncertainty-based approaches outperform other single-criterion approaches, though many works, primarily in Computer Vision, demonstrate that considering diversity reduces repetitive training examples and representativeness reduces outlier sampling (Roy and McCallum, 2001;Zhu et al, 2003;Settles and Craven, 2008;Zhu et al, 2008;Olsson, 2009;Gu et al, 2014;He et al, 2014;Yang et al, 2015;Wang et al, 2018b).…”

Section: Related Workmentioning

confidence: 99%

Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities

Erdmann¹,

Wrisley²,

Allen³

et al. 2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Scholars in inter-disciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora. Yet, under-resourced languages, imperfect or noisily structured data, and user-specific classification tasks make it difficult to meet their needs using off-the-shelf models. Manual annotation of large corpora from scratch, meanwhile, can be prohibitively expensive. Thus, we propose an active learning solution for named entity recognition, attempting to maximize a custom model's improvement per additional unit of manual annotation. Our system robustly handles any domain or user-defined label set and requires no external resources, enabling quality named entity recognition for Humanities corpora where such resources are not available. Evaluating on typologically disparate languages and datasets, we reduce required annotation by 20-60% and greatly outperform a competitive active learning baseline.

show abstract

Active learning combining uncertainty and diversity for multi‐class image classification

Cited by 29 publications

References 18 publications

A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data

A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data

Active Learning Methods for Efficient Hybrid Biophysical Variable Retrieval

Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities

Contact Info

Product

Resources

About