Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

Bhattarai, Binod; Sharma, Gaurav; Jurie, Frédéric; Pérez, Patrick

doi:10.1007/978-3-319-16181-5_12

Cited by 15 publications

(30 citation statements)

References 42 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In related applications, Bhattarai et al [16] develop a semisupervised method for organizing datasets for improved retrieval speed via hierarchical clustering. Tapaswi et al [17] address organization of video frames, performing both within video and cross-video clustering, incorporating constraints from face tracking and common video editing patterns.…”

Section: Face Clusteringmentioning

confidence: 99%

Clustering Millions of Faces by Identity

Otto

Wang

Jain

2018

IEEE Trans. Pattern Anal. Mach. Intell.

134

129

View full text Add to dashboard Cite

Abstract-In this work, we attempt to address the following problem: Given a large number of unlabeled face images, cluster them into the individual identities present in this data. We consider this a relevant problem in different application scenarios ranging from social media to law enforcement. In large-scale scenarios the number of faces in the collection can be of the order of hundreds of million, while the number of clusters can range from a few thousand to millions-leading to difficulties in terms of both run-time complexity and evaluating clustering and per-cluster quality. An efficient and effective Rank-Order clustering algorithm is developed to achieve the desired scalability, and better clustering accuracy than other well-known algorithms such as k-means and spectral clustering. We cluster up to 123 million face images into over 10 million clusters, and analyze the results in terms of both external cluster quality measures (known face labels) and internal cluster quality measures (unknown face labels) and run-time. Our algorithm achieves an F-measure of 0.87 on a benchmark unconstrained face dataset (LFW, consisting of 13K faces), and 0.27 on the largest dataset considered (13K images in LFW, plus 123M distractor images). Additionally, we present preliminary work on video frame clustering (achieving 0.71 F-measure when clustering all frames in the benchmark YouTube Faces dataset). A per-cluster quality measure is developed which can be used to rank individual clusters and to automatically identify a subset of good quality clusters for manual exploration.

show abstract

Section: Face Clusteringmentioning

confidence: 99%

Clustering Millions of Faces by Identity

Otto

Wang

Jain

2018

IEEE Trans. Pattern Anal. Mach. Intell.

134

129

View full text Add to dashboard Cite

show abstract

“…[20], sometimes by augmenting LFW images with other image sets [64]. Other authors have augmented the images in LFW to study image retrieval with large numbers of distractors [22]. However, the time is ripe for new databases and benchmarks designed specifically for new problems, especially identification problems.…”

Section: New Databases and Benchmarksmentioning

confidence: 99%

Labeled Faces in the Wild: A Survey

Learned-Miller

Huang

RoyChowdhury

et al. 2016

Advances in Face Detection and Facial Image Analysis

348

210

View full text Add to dashboard Cite

In 2007, Labeled Faces in the Wild was released in an effort to spur research in face recognition, specifically for the problem of face verification with unconstrained images. Since that time, more than 50 papers have been published that improve upon this benchmark in some respect. A remarkably wide variety of innovative methods have been developed to overcome the challenges presented in this database. As performance on some aspects of the benchmark approaches 100% accuracy, it seems appropriate to review this progress, derive what general principles we can from these works, and identify key future challenges in face recognition. In this survey, we review the contributions to LFW for which the authors have provided results to the curators (results found on the LFW results web page). We also review the cross cutting topic of alignment and how it is used in various methods. We end with a brief discussion of recent databases designed to challenge the next generation of face recognition algorithms.

show abstract

“…Metric Learning (ML) has been quite successful in various facial analysis tasks such as face recognition [14,15] and face retrieval [16]. Mahalanobis-like ML can be seen as learning a projection to map high dimensional features into a lower dimensional subspace where the pairwise constraints are better satisfied.…”

Section: Metric Learning and Its Application To Cross-domain Classifimentioning

confidence: 99%

A joint learning approach for cross domain age estimation

Bhattarai

Sharma

Lechervy

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

We propose a novel joint learning method for cross domain age estimation, a domain adaptation problem. The proposed method learns a low dimensional projection along with a regressor, in the projection space, in a joint framework. The projection aligns the features from two different domains, i.e. source and target, to the same space, while the regressor predicts the age from the domain aligned features. After this alignment, a regressor trained with only a few examples from the target domain, along with more examples from the source domain, can predict very well the ages of the target domain face images. We provide empirical validation on the largest publicly available dataset for age estimation i.e. MORPH-II. The proposed method improves performance over several strong baselines and the current state-of-the-art methods.

show abstract

Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

Cited by 15 publications

References 42 publications

Clustering Millions of Faces by Identity

Clustering Millions of Faces by Identity

Labeled Faces in the Wild: A Survey

A joint learning approach for cross domain age estimation

Contact Info

Product

Resources

About