scholarly journals Zero Shot Learning via Low-rank Embedded Semantic AutoEncoder

2018 ◽  
Author(s):  
Yang Liu ◽  
Quanxue Gao ◽  
Jin Li ◽  
Jungong Han ◽  
Ling Shao
Keyword(s):  
State Of The Art ◽  
Feature Space ◽  
Original Data ◽  
Semantic Space ◽  
Dimensional Subspace ◽  
Low Rank ◽  
Visual Features ◽  
Visual Feature ◽  
Benchmark Datasets ◽  
Low Dimensional

Zero-shot learning (ZSL) has been widely researched and get successful in machine learning. Most existing ZSL methods aim to accurately recognize objects of unseen classes by learning a shared mapping from the feature space to a semantic space. However, such methods did not investigate in-depth whether the mapping can precisely reconstruct the original visual feature. Motivated by the fact that the data have low intrinsic dimensionality e.g. low-dimensional subspace. In this paper, we formulate a novel framework named Low-rank Embedded Semantic AutoEncoder (LESAE) to jointly seek a low-rank mapping to link visual features with their semantic representations. Taking the encoder-decoder paradigm, the encoder part aims to learn a low-rank mapping from the visual feature to the semantic space, while decoder part manages to reconstruct the original data with the learned mapping. In addition, a non-greedy iterative algorithm is adopted to solve our model. Extensive experiments on six benchmark datasets demonstrate its superiority over several state-of-the-art algorithms.

scholarly journals Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature

2020 ◽  
Vol 34 (07) ◽  
pp. 11547-11554
Author(s):  
Bo Liu ◽  
Qiulei Dong ◽  
Zhanyi Hu
Keyword(s):  
State Of The Art ◽  
Feature Space ◽  
Visual Features ◽  
Selection Strategy ◽  
Semantic Features ◽  
Visual Feature ◽  
Adversarial Network ◽  
Benchmark Datasets ◽  
Residual Generator ◽  
Object Features

Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly overlapped, resulting in inaccurate object recognition. Addressing this problem, we propose a novel adversarial network to synthesize compact semantic visual features for ZSL, consisting of a residual generator, a prototype predictor, and a discriminator. The residual generator is to generate the visual feature residual, which is integrated with a visual prototype predicted via the prototype predictor for synthesizing the visual feature. The discriminator is to distinguish the synthetic visual features from the real ones extracted from an existing categorization CNN. Since the generated residuals are generally numerically much smaller than the distances among all the prototypes, the distributions of the unseen-class features synthesized by the proposed network are less overlapped. In addition, considering that the visual features from categorization CNNs are generally inconsistent with their semantic features, a simple feature selection strategy is introduced for extracting more compact semantic visual features. Extensive experimental results on six benchmark datasets demonstrate that our method could achieve a significantly better performance than existing state-of-the-art methods by ∼1.2-13.2% in most cases.

Robust subspace clustering based on latent low rank representation with non-negative sparse Laplacian constraints

2021 ◽  
pp. 1-15
Author(s):  
Zhixuan xu ◽  
Caikou Chen ◽  
Guojiang Han ◽  
Jun Gao
Keyword(s):  
State Of The Art ◽  
Subspace Clustering ◽  
Dimensional Subspace ◽  
Low Rank ◽  
Dimensional Structure ◽  
Clustering Methods ◽  
Benchmark Datasets ◽  
Handwritten Digit ◽  
Low Rank Representation ◽  
Low Dimensional

As a successful improvement on Low Rank Representation (LRR), Latent Low Rank Representation (LatLRR) has been one of the state-of-the-art models for subspace clustering due to the capability of discovering the low dimensional subspace structures of data, especially when the data samples are insufficient and/or extremely corrupted. However, the LatLRR method does not consider the nonlinear geometric structures within data, which leads to the loss of the locality information among data in the learning phase. Moreover, the coefficients of the learnt representation matrix can be negative, which lack the interpretability. To solve the above drawbacks of LatLRR, this paper introduces Laplacian, sparsity and non-negativity to LatLRR model and proposes a novel subspace clustering method, termed latent low rank representation with non-negative, sparse and laplacian constraints (NNSLLatLRR), in which we jointly take into account non-negativity, sparsity and laplacian properties of the learnt representation. As a result, the NNSLLatLRR can not only capture the global low dimensional structure and intrinsic non-linear geometric information of the data, but also enhance the interpretability of the learnt representation. Extensive experiments on two face benchmark datasets and a handwritten digit dataset show that our proposed method outperforms existing state-of-the-art subspace clustering methods.

scholarly journals A Co-Embedding Model with Variational Auto-Encoder for Knowledge Graphs

2022 ◽  
Vol 12 (2) ◽  
pp. 715
Author(s):  
Luodi Xie ◽  
Huimin Huang ◽  
Qing Du
Keyword(s):  
State Of The Art ◽  
Relation Extraction ◽  
Semantic Space ◽  
Knowledge Graph ◽  
High Quality ◽  
Gaussian Distributions ◽  
Benchmark Datasets ◽  
Semantic Spaces ◽  
Knowledge Graphs ◽  
Low Dimensional

Knowledge graph (KG) embedding has been widely studied to obtain low-dimensional representations for entities and relations. It serves as the basis for downstream tasks, such as KG completion and relation extraction. Traditional KG embedding techniques usually represent entities/relations as vectors or tensors, mapping them in different semantic spaces and ignoring the uncertainties. The affinities between entities and relations are ambiguous when they are not embedded in the same latent spaces. In this paper, we incorporate a co-embedding model for KG embedding, which learns low-dimensional representations of both entities and relations in the same semantic space. To address the issue of neglecting uncertainty for KG components, we propose a variational auto-encoder that represents KG components as Gaussian distributions. In addition, compared with previous methods, our method has the advantages of high quality and interpretability. Our experimental results on several benchmark datasets demonstrate our model’s superiority over the state-of-the-art baselines.

scholarly journals The Image Annotation Refinement in Embedding Feature Space based on Mutual Information

2022 ◽  
Vol 16 ◽  
pp. 191-201
Author(s):  
Wei Li ◽  
Haiyu Song ◽  
Hongda Zhang ◽  
Houjie Li ◽  
Pengjie Wang
Keyword(s):  
Mutual Information ◽  
Image Annotation ◽  
State Of The Art ◽  
Feature Space ◽  
Semantic Space ◽  
Visual Features ◽  
Novel Approach ◽  
Proposed Model ◽  
Information Method ◽  
Available Information

The ever-increasing size of images has made automatic image annotation one of the most important tasks in the fields of machine learning and computer vision. Despite continuous efforts in inventing new annotation algorithms and new models, results of the state-of-the-art image annotation methods are often unsatisfactory. In this paper, to further improve annotation refinement performance, a novel approach based on weighted mutual information to automatically refine the original annotations of images is proposed. Unlike the traditional refinement model using only visual feature, the proposed model use semantic embedding to properly map labels and visual features to a meaningful semantic space. To accurately measure the relevance between the particular image and its original annotations, the proposed model utilize all available information including image-to-image, label-to-label and image-to-label. Experimental results conducted on three typical datasets show not only the validity of the refinement, but also the superiority of the proposed algorithm over existing ones. The improvement largely benefits from our proposed mutual information method and utilizing all available information.

Dual discriminative auto-encoder network for zero shot image recognition

2021 ◽  
pp. 1-12
Author(s):  
Haoyue Bai ◽  
Haofeng Zhang ◽  
Qiong Wang
Keyword(s):  
Image Recognition ◽  
Feature Space ◽  
Semantic Space ◽  
High Dimensional ◽  
Visual Features ◽  
Discriminative Feature ◽  
Latent Space ◽  
Embedding Strategy ◽  
Low Dimensional ◽  
Semantic Attributes

Zero Shot learning (ZSL) aims to use the information of seen classes to recognize unseen classes, which is achieved by transferring knowledge of the seen classes from the semantic embeddings. Since the domains of the seen and unseen classes do not overlap, most ZSL algorithms often suffer from domain shift problem. In this paper, we propose a Dual Discriminative Auto-encoder Network (DDANet), in which visual features and semantic attributes are self-encoded by using the high dimensional latent space instead of the feature space or the low dimensional semantic space. In the embedded latent space, the features are projected to both preserve their original semantic meanings and have discriminative characteristics, which are realized by applying dual semantic auto-encoder and discriminative feature embedding strategy. Moreover, the cross modal reconstruction is applied to obtain interactive information. Extensive experiments are conducted on four popular datasets and the results demonstrate the superiority of this method.

scholarly journals Generative Image Inpainting with Submanifold Alignment

2019 ◽  
Author(s):  
Ang Li ◽  
Jianzhong Qi ◽  
Rui Zhang ◽  
Xingjun Ma ◽  
Kotagiri Ramamohanarao
Keyword(s):  
State Of The Art ◽  
Image Inpainting ◽  
Feature Space ◽  
Original Data ◽  
Local Data ◽  
Deep Feature ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Structural Consistency ◽  
Different Levels

Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based generative inpainting models do not explicitly exploit the structural or textural consistency between restored contents and their surrounding contexts. To address this limitation, we propose to enforce the alignment (or closeness) between the local data submanifolds (subspaces) around restored images and those around the original (uncorrupted) images during the learning process of GAN-based inpainting models. We exploit Local Intrinsic Dimensionality (LID) to measure, in deep feature space, the alignment between data submanifolds learned by a GAN model and those of the original data, from a perspective of both images (denoted as iLID) and local patches (denoted as pLID) of images. We then apply iLID and pLID as regularizations for GAN-based inpainting models to encourage two different levels of submanifold alignments: 1) an image-level alignment to improve structural consistency, and 2) a patch-level alignment to improve textural details. Experimental results on four benchmark datasets show that our proposed model can generate more accurate results than state-of-the-art models.

Multiview Common Subspace Clustering via Coupled Low Rank Representation

2021 ◽  
Vol 12 (4) ◽  
pp. 1-25
Author(s):  
Stanley Ebhohimhen Abhadiomhen ◽  
Zhiyang Wang ◽  
Xiangjun Shen ◽  
Jianping Fan
Keyword(s):  
Common Knowledge ◽  
Subspace Clustering ◽  
Laplacian Matrix ◽  
Low Rank ◽  
Connected Components ◽  
Similarity Matrix ◽  
Benchmark Datasets ◽  
Low Rank Representation ◽  
Low Dimensional ◽  
Shared Structure

Multi-view subspace clustering (MVSC) finds a shared structure in latent low-dimensional subspaces of multi-view data to enhance clustering performance. Nonetheless, we observe that most existing MVSC methods neglect the diversity in multi-view data by considering only the common knowledge to find a shared structure either directly or by merging different similarity matrices learned for each view. In the presence of noise, this predefined shared structure becomes a biased representation of the different views. Thus, in this article, we propose a MVSC method based on coupled low-rank representation to address the above limitation. Our method first obtains a low-rank representation for each view, constrained to be a linear combination of the view-specific representation and the shared representation by simultaneously encouraging the sparsity of view-specific one. Then, it uses the k -block diagonal regularizer to learn a manifold recovery matrix for each view through respective low-rank matrices to recover more manifold structures from them. In this way, the proposed method can find an ideal similarity matrix by approximating clustering projection matrices obtained from the recovery structures. Hence, this similarity matrix denotes our clustering structure with exactly k connected components by applying a rank constraint on the similarity matrix’s relaxed Laplacian matrix to avoid spectral post-processing of the low-dimensional embedding matrix. The core of our idea is such that we introduce dynamic approximation into the low-rank representation to allow the clustering structure and the shared representation to guide each other to learn cleaner low-rank matrices that would lead to a better clustering structure. Therefore, our approach is notably different from existing methods in which the local manifold structure of data is captured in advance. Extensive experiments on six benchmark datasets show that our method outperforms 10 similar state-of-the-art compared methods in six evaluation metrics.

scholarly journals SLRL4D: Joint Restoration of Subspace Low-Rank Learning and Non-Local 4-D Transform Filtering for Hyperspectral Image

2020 ◽  
Vol 12 (18) ◽  
pp. 2979
Author(s):  
Le Sun ◽  
Chengxun He ◽  
Yuhui Zheng ◽  
Songze Tang
Keyword(s):  
Hyperspectral Image ◽  
Dimensional Subspace ◽  
Low Rank ◽  
Spatial Correlations ◽  
Self Similarity ◽  
Multiple Datasets ◽  
Alternating Direction ◽  
Non Local ◽  
Low Dimensional ◽  
Spatial Redundancy

During the process of signal sampling and digital imaging, hyperspectral images (HSI) inevitably suffer from the contamination of mixed noises. The fidelity and efficiency of subsequent applications are considerably reduced along with this degradation. Recently, as a formidable implement for image processing, low-rank regularization has been widely extended to the restoration of HSI. Meanwhile, further exploration of the non-local self-similarity of low-rank images are proven useful in exploiting the spatial redundancy of HSI. Better preservation of spatial-spectral features is achieved under both low-rank and non-local regularizations. However, existing methods generally regularize the original space of HSI, the exploration of the intrinsic properties in subspace, which leads to better denoising performance, is relatively rare. To address these challenges, a joint method of subspace low-rank learning and non-local 4-d transform filtering, named SLRL4D, is put forward for HSI restoration. Technically, the original HSI is projected into a low-dimensional subspace. Then, both spectral and spatial correlations are explored simultaneously by imposing low-rank learning and non-local 4-d transform filtering on the subspace. The alternating direction method of multipliers-based algorithm is designed to solve the formulated convex signal-noise isolation problem. Finally, experiments on multiple datasets are conducted to illustrate the accuracy and efficiency of SLRL4D.

Out-of-sample data visualization using bi-kernel t-SNE

2020 ◽  
pp. 147387162097820
Author(s):  
Haili Zhang ◽  
Pu Wang ◽  
Xuejin Gao ◽  
Yongsheng Qi ◽  
Huihui Gao
Keyword(s):  
Data Visualization ◽  
Principal Component ◽  
Feature Space ◽  
Gaussian Kernel ◽  
Sample Data ◽  
Out Of Sample ◽  
Benchmark Datasets ◽  
The Difference ◽  
Low Dimensional ◽  
Effective Visualization

T-distributed stochastic neighbor embedding (t-SNE) is an effective visualization method. However, it is non-parametric and cannot be applied to steaming data or online scenarios. Although kernel t-SNE provides an explicit projection from a high-dimensional data space to a low-dimensional feature space, some outliers are not well projected. In this paper, bi-kernel t-SNE is proposed for out-of-sample data visualization. Gaussian kernel matrices of the input and feature spaces are used to approximate the explicit projection. Then principal component analysis is applied to reduce the dimensionality of the feature kernel matrix. Thus, the difference between inliers and outliers is revealed. And any new sample can be well mapped. The performance of the proposed method for out-of-sample projection is tested on several benchmark datasets by comparing it with other state-of-the-art algorithms.

scholarly journals Accurate prediction of DNA N4-methylcytosine sites via boost-learning various types of sequence features

BMC Genomics ◽  
2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Zhixun Zhao ◽  
Xiaocai Zhang ◽  
Fang Chen ◽  
Liang Fang ◽  
Jinyan Li
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Case Studies ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Feature Space ◽  
Sequence Features ◽  
Independent Test ◽  
Benchmark Datasets

Abstract Background DNA N4-methylcytosine (4mC) is a critical epigenetic modification and has various roles in the restriction-modification system. Due to the high cost of experimental laboratory detection, computational methods using sequence characteristics and machine learning algorithms have been explored to identify 4mC sites from DNA sequences. However, state-of-the-art methods have limited performance because of the lack of effective sequence features and the ad hoc choice of learning algorithms to cope with this problem. This paper is aimed to propose new sequence feature space and a machine learning algorithm with feature selection scheme to address the problem. Results The feature importance score distributions in datasets of six species are firstly reported and analyzed. Then the impact of the feature selection on model performance is evaluated by independent testing on benchmark datasets, where ACC and MCC measurements on the performance after feature selection increase by 2.3% to 9.7% and 0.05 to 0.19, respectively. The proposed method is compared with three state-of-the-art predictors using independent test and 10-fold cross-validations, and our method outperforms in all datasets, especially improving the ACC by 3.02% to 7.89% and MCC by 0.06 to 0.15 in the independent test. Two detailed case studies by the proposed method have confirmed the excellent overall performance and correctly identified 24 of 26 4mC sites from the C.elegans gene, and 126 out of 137 4mC sites from the D.melanogaster gene. Conclusions The results show that the proposed feature space and learning algorithm with feature selection can improve the performance of DNA 4mC prediction on the benchmark datasets. The two case studies prove the effectiveness of our method in practical situations.

Sign in / Sign up

Export Citation Format

Share Document