Recent Advances in Open Set Recognition: A Survey

Geng, Chuanxing; Huang, Sheng-Jun; Chen, Songcan

doi:10.1109/tpami.2020.2981604

Cited by 590 publications

(313 citation statements)

References 155 publications

(293 reference statements)

Supporting

Mentioning

311

Contrasting

Order By: Relevance

“…The problem of OOD detection has been investigated in many contexts with different alias, such as "anomaly detection" [15], "one-class classification" [18], [19], "open-set recognition" [20], or "novelty detection" [21]. Significant results have been achieved by conventional methods in lowdimensional spaces [19], [22], and some of these methods have also been applied to NLU systems [23], [24].…”

Section: Related Workmentioning

confidence: 99%

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Zheng

Chen

Huang

2020

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Natural Language Understanding (NLU) is a vital component of dialogue systems, and its ability to detect Out-of-Domain (OOD) inputs is critical in practical applications, since the acceptance of the OOD input that is unsupported by the current system may lead to catastrophic failure. However, most existing OOD detection methods rely heavily on manually labeled OOD samples and cannot take full advantage of unlabeled data. This limits the feasibility of these models in practical applications.In this paper, we propose a novel model to generate highquality pseudo OOD samples that are akin to IN-Domain (IND) input utterances, and thereby improves the performance of OOD detection. To this end, an autoencoder is trained to map an input utterance into a latent code. and the codes of IND and OOD samples are trained to be indistinguishable by utilizing a generative adversarial network. To provide more supervision signals, an auxiliary classifier is introduced to regularize the generated OOD samples to have indistinguishable intent labels. Experiments show that these pseudo OOD samples generated by our model can be used to effectively improve OOD detection in NLU. Besides, we also demonstrate that the effectiveness of these pseudo OOD data can be further improved by efficiently utilizing unlabeled data.

show abstract

Section: Related Workmentioning

confidence: 99%

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Zheng

Chen

Huang

2020

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…The evaluation of openworld classification is critical and diverse because of the inclusion of unknown classes [68]. A naive solution is extending the current OA evaluation metric from C classes to C + 1 classes, where the added is the unknown class.…”

Section: Datasets and Experimental Setupmentioning

confidence: 99%

Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning

Liu

Shi

Zhang

2021

IEEE Trans. Geosci. Remote Sensing

195

View full text Add to dashboard Cite

Current hyperspectral image classification assumes that a predefined classification system is closed and complete, and there are no unknown or novel classes in the unseen data. However, this assumption may be too strict for the real world. Often, novel classes are overlooked when the classification system is constructed. The closed nature forces a model to assign a label given a new sample and may lead to overestimation of known land covers (e.g., crop area). To tackle this issue, we propose a multitask deep learning method that simultaneously conducts classification and reconstruction in the open world (named MDL4OW) where unknown classes may exist. The reconstructed data are compared with the original data; those failing to be reconstructed are considered unknown, based on the assumption that they are not well represented in the latent features due to the lack of labels. A threshold needs to be defined to separate the unknown and known classes; we propose two strategies based on the extreme value theory for few-shot and manyshot scenarios. The proposed method was tested on real-world hyperspectral images; state-of-the-art results were achieved, e.g., improving the overall accuracy by 4.94% for the Salinas data. By considering the existence of unknown classes in the open world, our method achieved more accurate hyperspectral image classification, especially under the few-shot context.

show abstract

“…Till now, although various ZSL methods have been proposed [44], all these methods are limited to classification or prediction scenario [45]. To our best knowledge, there is little reported work considering the unseen classes in the network embedding problem.…”

Section: Zero-shot Learningmentioning

confidence: 99%

Network Embedding With Completely-Imbalanced Labels

Wang

Yao

Wang

et al. 2021

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no labeled nodes at all. To alleviate this, we propose two novel semi-supervised network embedding methods. The first one is a shallow method named RSDNE. Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. The other method is RECT which is a new class of graph neural networks. Different from RSDNE, to benefit from the completely-imbalanced labels, RECT explores the class-semantic knowledge. This enables RECT to handle networks with node features and multi-label setting. Experimental results on several real-world datasets demonstrate the superiority of the proposed methods.

show abstract

Recent Advances in Open Set Recognition: A Survey

Cited by 590 publications

References 155 publications

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning

Network Embedding With Completely-Imbalanced Labels

Contact Info

Product

Resources

About