Towards open-set face recognition using hashing functions

Vareto, Rafael Henrique; Silva, Samira; Costa, Filipe; Schwartz, William Robson

doi:10.1109/btas.2017.8272751

Cited by 34 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first SVM is a one-class SVM CAP model used as a conditioner: if the posterior estimate P O (y|x) of an input sample x predicted by one-class SVM is less than a threshold δ τ , the sample will be rejected outright. Otherwise, OSR Discriminative Model (DM) SVM-based [21], [65]- [69] + EVT TML-based [22], [23] SR-based [61] + EVT Dis-based [70], [71] MD-based [72], [73] + EVT Others [74], [75], [76] DNN-based [25], [64], [79], [81]- [84] + EVT [77], [78], [80], [85] Generative Model (GM)…”

Section: A Categorization Of Osr Techniquesmentioning

confidence: 99%

Recent Advances in Open Set Recognition: A Survey

Geng

Huang

Chen

2021

IEEE Trans. Pattern Anal. Mach. Intell.

590

268

View full text Add to dashboard Cite

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with the unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also overview the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.

show abstract

Section: A Categorization Of Osr Techniquesmentioning

confidence: 99%

Recent Advances in Open Set Recognition: A Survey

Geng

Huang

Chen

2021

IEEE Trans. Pattern Anal. Mach. Intell.

590

268

View full text Add to dashboard Cite

show abstract

“…Experiments performed on Experiment 4 of FRGCv1 dataset (Experiment 4) [9] achieved state-of-the-art results for small galleries in comparison with published work [7].…”

Section: Introductionmentioning

confidence: 76%

“…For such, the evaluation metrics, datasets employed and the experimental protocols are described. For literature comparison, we chose the work of Vareto et al [7], taking into account the clarity on the evaluation protocol which assists reproducibility of experiments, enabling a fair comparison.…”

Section: Methodsmentioning

confidence: 99%

“…For that reason, scalability is drawing the attention of several researchers [14], [18]- [20]. Vareto et al [7] concentrate on the open-set face recognition problem as they assess both Partial Least Squares (PLS) and Multi-Layer Perceptron (MLP) classification models in pursuance of an algorithm that is not directly dependent on the gallery set size. In fact, the authors build a collection of either PLS or MLP binary models, defined as hashing functions, and a voting system scheme (candidate list) to determine whether the queried subject is known or unknown.…”

Section: Related Workmentioning

confidence: 99%

“…As we are comparing our proposal to the one by Vareto et al [7], and their protocol is well described, we used their protocol, which we refer to as Experimental Protocol I.…”

Section: Experimental Protocolsmentioning

confidence: 99%

See 2 more Smart Citations

Open-set Face Recognition for Small Galleries Using Siamese Networks

Salomon

Britto

Vareto

et al. 2020

2020 International Conference on Systems, Signals and Image Processing (IWSSIP)

View full text Add to dashboard Cite

Face recognition has been one of the most relevant and explored fields of Biometrics. In real-world applications, face recognition methods usually must deal with scenarios where not all probe individuals were seen during the training phase (openset scenarios). Therefore, open-set face recognition is a subject of increasing interest as it deals with identifying individuals in a space where not all faces are known in advance. This is useful in several applications, such as access authentication, on which only a few individuals that have been previously enrolled in a gallery are allowed. The present work introduces a novel approach towards open-set face recognition focusing on small galleries and in enrollment detection, not identity retrieval. A Siamese Network architecture is proposed to learn a model to detect if a face probe is enrolled in the gallery based on a verification-like approach. Promising results were achieved for small galleries on experiments carried out on Pubfig83, FRGCv1 and LFW datasets. State-ofthe-art methods like HFCN and HPLS were outperformed on FRGCv1. Besides, a new evaluation protocol is introduced for experiments in small galleries on LFW.

show abstract