Disambiguation-Free Partial Label Learning

Zhang, Min-Ling

doi:10.1137/1.9781611973440.5

Cited by 49 publications

(83 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a photograph might contain many faces with captions listing who is in the photo but the names are not matched to the face. Many methods for learning partial labels have been developed to recover the ground-truth labels from a candidate set [291], [292]. However, most are based on the assumption of exactly one ground truth for each instance, which may not always hold true by different label annotation methods.…”

Section: E Veracity -Noisy Output Labelsmentioning

confidence: 99%

Survey on Multi-Output Learning

Shi

Tsang

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

169

View full text Add to dashboard Cite

The aim of multi-output learning is to simultaneously predict multiple outputs given an input. It is an important learning problem for decision-making, since making decisions in the real world often involves multiple complex factors and criteria. In recent times, an increasing number of research studies have focused on ways to predict multiple outputs at once. Such efforts have transpired in different forms according to the particular multi-output learning problem under study. Classic cases of multi-output learning include multi-label learning, multidimensional learning, multi-target regression and others. From our survey of the topic, we were struck by a lack in studies that generalize the different forms of multi-output learning into a common framework. This paper fills that gap with a comprehensive review and analysis of the multi-output learning paradigm. In particular, we characterize the 4 Vs of multi-output learning, i.e., volume, velocity, variety, and veracity, and the ways in which the 4 Vs both benefit and bring challenges to multioutput learning by taking inspiration from big data. We analyze the life cycle of output labeling, present the main mathematical definitions of multi-output learning, and examine the field's key challenges and corresponding solutions as found in the literature. Several model evaluation metrics and popular data repositories are also discussed. Last but not least, we highlight some emerging challenges with multi-output learning from the perspective of the 4 Vs as potential research directions worthy of further studies.

show abstract

Section: E Veracity -Noisy Output Labelsmentioning

confidence: 99%

Survey on Multi-Output Learning

Shi

Tsang

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

169

View full text Add to dashboard Cite

show abstract

“…Subsequently, a discriminative classifier can be learned from the ambiguous labels by minimizing the partial 0/1 loss. Several works have improved the learning of partial labels with the modeling of partial loss [23], error-correcting output codes [24], and iterative label propagation [25]. Liu et al [6] proposed to learn a conditional multinomial mixture model for predicting the actual label from ambiguous labels.…”

Section: Related Workmentioning

confidence: 99%

Learning from Ambiguously Labeled Face Images

Chen

Patel

Chellappa

2018

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the caption. We propose a Matrix Completion for Ambiguity Resolution (MCar) method for predicting the actual labels from ambiguously labeled images. This step is followed by learning a standard supervised classifier from the disambiguated labels to classify new images. To prevent the majority labels from dominating the result of MCar, we generalize MCar to a weighted MCar (WMCar) that handles label imbalance. Since WMCar outputs a soft labeling vector of reduced ambiguity for each instance, we can iteratively refine it by feeding it as the input to WMCar. Nevertheless, such an iterative implementation can be affected by the noisy soft labeling vectors, and thus the performance may degrade. Our proposed Iterative Candidate Elimination (ICE) procedure makes the iterative ambiguity resolution possible by gradually eliminating a portion of least likely candidates in ambiguously labeled face. We further extend MCar to incorporate the labeling constraints between instances when such prior knowledge is available. Compared to existing methods, our approach demonstrates improvement on several ambiguously labeled datasets.

show abstract

“…To test the classification ability of different methods on ambiguous image classification, we follow [1] and [17] and use the MSRCv2 dataset for our comparison. This dataset contains 591 natural images with totally 23 classes.…”

Section: B Ambiguous Image Classificationmentioning

confidence: 99%

A Regularization Approach for Instance-Based Superset Label Learning

Gong

Liu

Tang

et al. 2018

IEEE Trans. Cybern.

102

View full text Add to dashboard Cite

Different from the traditional supervised learning in which each training example has only one explicit label, superset label learning (SLL) refers to the problem that a training example can be associated with a set of candidate labels, and only one of them is correct. Existing SLL methods are either regularization-based or instance-based, and the latter of which has achieved state-of-the-art performance. This is because the latest instance-based methods contain an explicit disambiguation operation that accurately picks up the groundtruth label of each training example from its ambiguous candidate labels. However, such disambiguation operation does not fully consider the mutually exclusive relationship among different candidate labels, so the disambiguated labels are usually generated in a nondiscriminative way, which is unfavorable for the instance-based methods to obtain satisfactory performance. To address this defect, we develop a novel regularization approach for instance-based superset label (RegISL) learning so that our instance-based method also inherits the good discriminative ability possessed by the regularization scheme. Specifically, we employ a graph to represent the training set, and require the examples that are adjacent on the graph to obtain similar labels. More importantly, a discrimination term is proposed to enlarge the gap of values between possible labels and unlikely labels for every training example. As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms. The experimental results on various tasks convincingly demonstrate the superiority of our RegISL to other typical SLL methods in terms of both training accuracy and test accuracy.

show abstract

Disambiguation-Free Partial Label Learning

Cited by 49 publications

References 15 publications

Survey on Multi-Output Learning

Survey on Multi-Output Learning

Learning from Ambiguously Labeled Face Images

A Regularization Approach for Instance-Based Superset Label Learning

Contact Info

Product

Resources

About