Privileged Multi-label Learning

You, Suya; Xu, Chang; Wang, Yunhe; Xu, C.; Tao, Dacheng

doi:10.24963/ijcai.2017/466

Cited by 25 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hamming loss measures the proportion of inconsistencies between the predicted and the ground-truth labels. Since it is separable for each label, its continuous surrogate losses [16]- [18] can be easily optimized. However, the dependencies among labels are not captured in these losses, while the label dependencies often play important role in multi-label learning.…”

Section: Related Workmentioning

confidence: 99%

Groupwise Ranking Loss for Multi-Label Learning

Fan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This work studies multi-label learning (MLL), where each instance is associated with a subset of positive labels. For each instance, a good multi-label predictor should encourage the predicted positive labels to be close to its ground-truth positive ones. In this work, we propose a new loss, named Groupwise Ranking LosS (GRLS) for multi-label learning. Minimizing GRLS encourages the predicted relevancy scores of the ground-truth positive labels to be higher than that of the negative ones. More importantly, its time complexity is linear with respect to the number of candidate labels, rather than square complexity for some pairwise ranking based methods. We further analyze GRLS in the perspective of label-wise margin and suggest that multi-label predictor is label-wise effective if and only if GRLS is optimal. We also analyze the relations between GRLS and some widely used loss functions for MLL. Finally, we apply GRLS to multi-label learning, and extensive experiments on several benchmark multi-label databases demonstrate the competitive performance of the proposed method to state-of-the-art methods. INDEX TERMS Multi-label learning, groupwise ranking, optimization.

show abstract

Section: Related Workmentioning

confidence: 99%

Groupwise Ranking Loss for Multi-Label Learning

Fan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In [47], the authors present an additional sparse component to deal with the tail labels for the multi-label learning task. In [50], You et al present the privileged multi-label learning (PrML) method to exploit the correlation between labels. For the problem of multi-label learning with missing labels, Jain et al [48] develop a scalable and generative framework, which is based on a latent factor model for the label matrix and an exposure model for missing labels.…”

Section: Multi-label Learningmentioning

confidence: 99%

Multi-label learning based deep transfer neural network for facial attribute classification

Zhuang

Yan

Chen

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

Deep Neural Network (DNN) has recently achieved outstanding performance in a variety of computer vision tasks, including facial attribute classification. The great success of classifying facial attributes with DNN often relies on a massive amount of labelled data. However, in real-world applications, labelled data are only provided for some commonly used attributes (such as age, gender); whereas, unlabelled data are available for other attributes (such as attraction, hairline). To address the above problem, we propose a novel deep transfer neural network method based on multi-label learning for facial attribute classification, termed FMTNet, which consists of three sub-networks: the Face detection Network (FNet), the Multi-label learning Network (MNet) and the Transfer learning Network (TNet). Firstly, based on the Faster Region-based Convolutional Neural Network (Faster R-CNN), FNet is finetuned for face detection. Then, MNet is fine-tuned by FNet to predict multiple attributes with labelled data, where an effective loss weight scheme is developed to explicitly exploit the correlation between facial attributes based on attribute grouping. Finally, based on MNet, TNet is trained by taking advantage of unsupervised domain adaptation for unlabelled facial attribute classification. The three sub-networks are tightly coupled to perform effective facial attribute classification. A distinguishing characteristic of the proposed FMTNet method is that the three sub-networks (FNet, MNet and TNet) are constructed in a similar network structure. Extensive experimental results on challenging face datasets demonstrate the effectiveness of our proposed method compared with several state-of-the-art methods.

show abstract

“…In the era of big data, content-based multimedia data retrieval has become increasingly difficult. Simultaneously, efficient indexing and search algorithms are receiving increasing attention [6,8,29,37,55,58]. However, when the amount of data is very large, the speed of exact nearest neighbor searches will drop dramatically.…”

Section: Introductionmentioning

confidence: 99%

Autoencoder-based unsupervised clustering and hashing

Zhang

Qian

2020

Appl Intell

View full text Add to dashboard Cite

Faced with a large amount of data and high-dimensional data information in a database, the existing exact nearest neighbor retrieval methods cannot obtain ideal retrieval results within an acceptable retrieval time. Therefore, researchers have begun to focus on approximate nearest neighbor retrieval. Recently, the hashing-based approximate nearest neighbor retrieval method has attracted increasing attention because of its small storage space and high retrieval efficiency. The development of neural networks has also promoted progress in hash learning. However, these methods are mostly supervised. In practical applications, annotating large amounts of data is a very time-consuming and laborious task. Furthermore, efficiently using a large amount of unlabeled data for hash learning is challenging. In this paper, we create a new autoencoder variant to efficiently capture the features of high-dimensional data, and propose an unsupervised deep hashing method for large-scale data retrieval, named as Autoencoder-based Unsupervised Clustering and Hashing (AUCH). By constructing a hashing layer as a hidden layer of the autoencoder, hash learning is performed together with unsupervised clustering by minimizing the overall loss. AUCH can unify unsupervised clustering and retrieval tasks into a single learning model. In addition, the method can use a deep neural network to simultaneously learn feature representations, hashing functions and cluster assignments. Experimental results on standard datasets indicate that AUCH achieves competitive results compared to state-of-the-art models for retrieval and clustering tasks.

show abstract

Privileged Multi-label Learning

Cited by 25 publications

References 16 publications

Groupwise Ranking Loss for Multi-Label Learning

Groupwise Ranking Loss for Multi-Label Learning

Multi-label learning based deep transfer neural network for facial attribute classification

Autoencoder-based unsupervised clustering and hashing

Contact Info

Product

Resources

About