Image Classification by Cross-Media Active Learning With Privileged Information

Yan, Yan; Nie, Feiping; Li, Wen; Gao, Chenqiang; Yang, Yi; Xu, Dong

doi:10.1109/tmm.2016.2602938

Cited by 139 publications

(34 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the curvature-related terms will bring extra computational complexity due to the existence of nonlinear higherorder derivatives. This issue also appears in other variational models such as the nontexture image inpainting [20] and image denoising [21] with features (edge, corner, smoothness, contrast, etc.) preservation.…”

Section: Introductionmentioning

confidence: 90%

A Novel Euler’s Elastica-Based Segmentation Approach for Noisy Images Using the Progressive Hedging Algorithm

Tan

Liu

et al. 2019

J Math Imaging Vis

View full text Add to dashboard Cite

Eulers elastica based unsupervised segmentation models have strong capability of completing the missing boundaries for existing objects in a clean image, but they are not working well for noisy images. This paper aims to establish a Eulers elastica based approach that properly deals with the random noises to improve the segmentation performance for noisy images. We solve the corresponding optimization problem via using the progressive hedging algorithm (PHA) with a step length suggested by the alternating direction method of multipliers (ADMM). Technically, all the simplified convex versions of the sub problems derived from the major framework of PHA can be obtained by using the curvature weighted approach and the convex relaxation method. Then an alternating optimization strategy is applied with the merits of using some powerful accelerating techniques including the fast Fourier transform (FFT) and generalized soft threshold formulas. Extensive experiments have been conducted on both synthetic and real images, which validated some significant gains of the proposed segmentation models and demonstrated the advantages of the developed algorithm.

show abstract

Section: Introductionmentioning

confidence: 90%

A Novel Euler’s Elastica-Based Segmentation Approach for Noisy Images Using the Progressive Hedging Algorithm

Tan

Liu

et al. 2019

J Math Imaging Vis

View full text Add to dashboard Cite

show abstract

“…We first transfer the original dataset into three different styles by Adobe Photoshop (PS) 1 . These three transferred datasets accompanying with the original dataset are regarded as four classes to fine-tune the classification model [48,17,52,11,65,62,18]. The fine-tuned feature of the average-pooling layer thus has the style-discriminative characteristic, because the style information is learned in the training procedure by machine-generated style supervision.…”

Section: Style-aggregated Face Generation Modulementioning

confidence: 99%

Style Aggregated Network for Facial Landmark Detection

Dong

Yan

Ouyang

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

273

212

View full text Add to dashboard Cite

Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g., grayscale vs. color images, light vs. dark, intense vs. dull, and so on, has constantly been overlooked. This issue becomes inevitable as increasing web images are collected from various sources for training neural networks. In this work, we propose a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection. Our method transforms original face images to style-aggregated images by a generative adversarial module. The proposed scheme uses the style-aggregated image to maintain face images that are more robust to environmental changes. Then the original face images accompanying with style-aggregated ones play a duet to train a landmark detector which is complementary to each other. In this way, for each face, our method takes two images as input, i.e., one in its original style and the other in the aggregated style. In experiments, we observe that the large variance of image styles would degenerate the performance of facial landmark detectors. Moreover, we show the robustness of our method to the large variance of image styles by comparing to a variant of our approach, in which the generative adversarial module is removed, and no style-aggregated images are used. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on benchmark datasets AFLW and 300-W. Code is publicly available on GitHub: https://github.com/D-X-Y/SAN

show abstract

“…It is equivalent to learning an oracle that tells which sample is easy or hard to be predicted. This paradigm has been used for multiple tasks, such as hashing [41], action and event recognition [42], information bottleneck learning [43], learning to rank [44], image categorization [45], object localization [46], and active learning [47], etc.…”

Section: Learning Using Privileged Informationmentioning

confidence: 99%

Person Re-Identification With Metric Learning Using Privileged Information

Yang

Wang

Tao

2018

IEEE Trans. on Image Process.

162

View full text Add to dashboard Cite

Despite the promising progress made in recent years, person re-identification remains a challenging task due to complex variations in human appearances from different camera views. This paper presents a logistic discriminant metric learning method for this challenging problem. Different with most existing metric learning algorithms, it exploits both original data and auxiliary data during training, which is motivated by the new machine learning paradigm-learning using privileged information. Such privileged information is a kind of auxiliary knowledge, which is only available during training. Our goal is to learn an optimal distance function by constructing a locally adaptive decision rule with the help of privileged information. We jointly learn two distance metrics by minimizing the empirical loss penalizing the difference between the distance in the original space and that in the privileged space. In our setting, the distance in the privileged space functions as a local decision threshold, which guides the decision making in the original space like a teacher. The metric learned from the original space is used to compute the distance between a probe image and a gallery image during testing. In addition, we extend the proposed approach to a multi-view setting which is able to explore the complementation of multiple feature representations. In the multi-view setting, multiple metrics corresponding to different original features are jointly learned, guided by the same privileged information. Besides, an effective iterative optimization scheme is introduced to simultaneously optimize the metrics and the assigned metric weights. Experiment results on several widely-used data sets demonstrate that the proposed approach is superior to global decision threshold-based methods and outperforms most state-of-the-art results.

show abstract

Image Classification by Cross-Media Active Learning With Privileged Information

Cited by 139 publications

References 26 publications

A Novel Euler’s Elastica-Based Segmentation Approach for Noisy Images Using the Progressive Hedging Algorithm

A Novel Euler’s Elastica-Based Segmentation Approach for Noisy Images Using the Progressive Hedging Algorithm

Style Aggregated Network for Facial Landmark Detection

Person Re-Identification With Metric Learning Using Privileged Information

Contact Info

Product

Resources

About