Learning by Associating Ambiguously Labeled Images

Zeng, Zinan; Xiao, Shijie; Jia, Kui; Chan, Tsung-Han; Gao, Shenghua; Xu, Dong; Ma, Yi

doi:10.1109/cvpr.2013.97

Cited by 117 publications

(72 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, there is an increasing research interest in developing automatic techniques for face naming in images [3], [4], [5], [6], [7], [8], [9] as well as in videos [10], [11], [12], [13]. To tag faces in news photos, Berg et al [3] proposed to cluster the faces in the news images.…”

Section: Related Workmentioning

confidence: 99%

“…In [7], Luo and Orabona proposed a Structural SVM-like algorithm called Maximum Margin Set (MMS) to solve the face naming problem. Recently, in [9], Zeng et al proposed the Low-Rank SVM (LR-SVM) approach to deal with this problem, based on the assumption that the feature matrix formed by faces from the same subject is low-rank. In the following, we compare our proposed approaches with several related existing methods.…”

Section: Related Workmentioning

confidence: 99%

“…Our rLRR method is related to LRR [2] and LR-SVM [9]. LRR is an unsupervised approach for exploring multiple subspace structures of data.…”

Section: Related Workmentioning

confidence: 99%

“…In contrast to LRR, our rLRR utilizes the weak supervision from image captions and also considers the image-level constraints when solving the weakly supervised face naming problem. Moreover, our rLRR differs from LR-SVM [9] in the following two aspects: 1) To utilize the weak supervision, LR-SVM considers weak supervision information in the partial permutation matrices, while rLRR uses our proposed regularizer to penalize the corresponding reconstruction coefficients. 2) LR-SVM is based on Robust PCA [14] [15] which is not a reconstruction based method, while our rLRR is related to the reconstruction based approach LRR.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Face Naming by Learning Discriminative Affinity Matrices From Weakly Labeled Images

Xiao

2015

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

Abstract-Given a collection of images, where each image contains several faces and is associated with a few names in the corresponding caption, the goal of face naming is to infer the correct name for each face. In this work, we propose two new methods to effectively solve this problem by learning two discriminative affinity matrices from these weakly labeled images. We first propose a new method called regularized low-rank representation (rLRR), by effectively utilizing weakly supervised information to learn a low-rank reconstruction coefficient matrix while exploring multiple subspace structures of the data. Specifically, by introducing a specially designed regularizer to the low-rank representation (LRR) method, we penalize the corresponding reconstruction coefficients related to the situations where a face is reconstructed by using face images from other subjects or by using itself. With the inferred reconstruction coefficient matrix, a discriminative affinity matrix can be obtained. Moreover, we also develop a new distance metric learning method called Ambiguously-supervised Structural Metric Learning (ASML) by using weakly supervised information to seek a discriminative distance metric. Hence, another discriminative affinity matrix can be obtained by using the similarity matrix (i.e., the kernel matrix) based on the Mahalanobis distances of the data. Observing that these two affinity matrices contain complementary information, we further combine them to obtain a fused affinity matrix, based on which we develop a new iterative scheme to infer the name of each face. Comprehensive experiments demonstrate the effectiveness of our approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Our rLRR method is related to LRR [2] and LR-SVM [9]. LRR is an unsupervised approach for exploring multiple subspace structures of data.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Face Naming by Learning Discriminative Affinity Matrices From Weakly Labeled Images

Xiao

2015

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The need to learn from data with partial labels arises in many real-world applications such as automatic face naming in videos [9] and webpages [15], image classification [23], bird song classification [17], etc.…”

Section: Introductionmentioning

confidence: 99%

Disambiguation-Free Partial Label Learning

Zhang

2014

Proceedings of the 2014 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Partial label learning deals with the problem where each training example is associated with a set of candidate labels, among which only one is correct. The common strategy is to try to disambiguate their candidate labels, such as by identifying the ground-truth label iteratively or by treating each candidate label equally. Nevertheless, the above disambiguation strategy is prone to be misled by the false positive label(s) within candidate label set. In this paper, a new disambiguation-free approach to partial label learning is proposed by employing the well-known error-correcting output codes (ECOC) techniques. Specifically, to build the binary classifier with respect to each column coding, any partially labeled example will be regarded as a positive or negative training example only if its candidate label set entirely falls into the coding dichotomy. Experiments on controlled and real-world data sets clearly validate the effectiveness of the proposed approach.

show abstract

Partial Label Learning by Entropy Minimization

Han

2020

Advances in Artificial Intelligence

View full text Add to dashboard Cite

Learning by Associating Ambiguously Labeled Images

Abstract: We study in this paper the problem of learning classifiers from ambiguously labeled images. For

Cited by 117 publications

References 24 publications

Automatic Face Naming by Learning Discriminative Affinity Matrices From Weakly Labeled Images

Automatic Face Naming by Learning Discriminative Affinity Matrices From Weakly Labeled Images

Disambiguation-Free Partial Label Learning

Partial Label Learning by Entropy Minimization

Contact Info

Product

Resources

About