“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Video indexing and retrieval have a wide spectrum of promising applications, motivating the interest of researchers worldwide. This paper offers a tutorial and an overview of the landscape of general strategies in visual content-based video indexing and retrieval, focusing on methods for video structure analysis, including shot boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, video retrieval including query interfaces, similarity measure and relevance feedback, and video browsing. Finally, we analyze future research directions.

A Survey on Visual Content-Based Video Indexing and Retrieval

Classification is one of the most researched questions in machine learning and data mining. A wide range of real problems have been stated as classification problems, for example credit scoring, bankruptcy prediction, medical diagnosis, pattern recognition, text categorization, software quality assessment, and many more. The use of evolutionary algorithms for training classifiers has been studied in the past few decades. Genetic programming (GP) is a flexible and powerful evolutionary technique with some features that can be very valuable and suitable for the evolution of classifiers. This paper surveys existing literature about the application of genetic programming to classification, to show the different ways in which this evolutionary algorithm can help in the construction of accurate and reliable classifiers.

A Survey on the Application of Genetic Programming to Classification

We propose a generative model for robust tensor factorization in the presence of both missing data and outliers. The objective is to explicitly infer the underlying low-CANDECOMP/PARAFAC (CP)-rank tensor capturing the global information and a sparse tensor capturing the local information (also considered as outliers), thus providing the robust predictive distribution over missing entries. The low-CP-rank tensor is modeled by multilinear interactions between multiple latent factors on which the column sparsity is enforced by a hierarchical prior, while the sparse tensor is modeled by a hierarchical view of Student- $t$ distribution that associates an individual hyperparameter with each element independently. For model learning, we develop an efficient variational inference under a fully Bayesian treatment, which can effectively prevent the overfitting problem and scales linearly with data size. In contrast to existing related works, our method can perform model selection automatically and implicitly without the need of tuning parameters. More specifically, it can discover the groundtruth of CP rank and automatically adapt the sparsity inducing priors to various types of outliers. In addition, the tradeoff between the low-rank approximation and the sparse representation can be optimized in the sense of maximum model evidence. The extensive experiments and comparisons with many state-of-the-art algorithms on both synthetic and real-world data sets demonstrate the superiorities of our method from several perspectives.

/pdf/bayesian-robust-tensor-factorization-for-incomplete-multiway-2oi047dji3.pdf

Bayesian Robust Tensor Factorization for Incomplete Multiway Data

Recently, the wide deployment of practical face recognition systems gives rise to the emergence of the inter-modality face recognition problem. In this problem, the face images in the database and the query images captured on spot are acquired under quite different conditions or even using different equipments. Conventional approaches either treat the samples in a uniform model or introduce an intermediate conversion stage, both of which would lead to severe performance degradation due to the great discrepancies between different modalities. In this paper, we propose a novel algorithm called Common Discriminant Feature Extraction specially tailored to the inter-modality problem. In the algorithm, two transforms are simultaneously learned to transform the samples in both modalities respectively to the common feature space. We formulate the learning objective by incorporating both the empirical discriminative power and tlie local smoothness of the feature transformation. By explicitly controlling the model complexity through the smoothness constraint, we can effectively reduce the risk of overfitting and enhance the generalization capability. Furthermore, to cope with the nongaussian distribution and diverse variations in the sample space, we develop two non-linear extensions of the algorithm: one is based on kernelization, while the other is a multi-mode framework. These extensions substantially improve the recognition performance in complex situation. Extensive experiments are conducted to test our algorithms in two application scenarios: optical image-infrared image recognition and photo-sketch recognition. Our algorithms show excellent performance in the experiments.

Inter-modality Face Recognition

Background modeling plays an important role in many applications of computer vision such as anomaly detection and visual tracking. Most existing algorithms for learning appearance model are vector-based methods without maintaining the 2D spatial structure information of objects in an image. To this end, a robust tensor subspace learning algorithm is developed for background modeling which can capture the appearance changes through adaptively updating the tensor subspace. In the tensor framework, the spatial structure information is maintained and utilized for feature extraction of objects. Then by incorporating the robust scheme, we can weight individual pixel of an image to reduce the influence of outliers on background modeling. Furthermore an incremental algorithm for the robust tensor subspace learning is proposed to adapt to the variation of appearance model. The experimental results illustrate the effectiveness of the proposed robust learning algorithm for anomaly detection.

Robust tensor subspace learning for anomaly detection

Cephalometric tracing method is usually used in orthodontic diagnosis and treatment planning. In this paper, we propose a deep learning based framework to automatically detect anatomical landmarks in cephalometric X-ray images. We train the deep encoder-decoder for landmark detection, and combine global landmark configuration with local high-resolution feature responses. The proposed frame-work is based on 2-stage u-net, regressing the multi-channel heatmaps for land-mark detection. In this framework, we embed attention mechanism with global stage heatmaps, guiding the local stage inferring, to regress the local heatmap patches in a high resolution. Besides, the Expansive Exploration strategy improves robustness while inferring, expanding the searching scope without increasing model complexity. We have evaluated our framework in the most widely-used public dataset of landmark detection in cephalometric X-ray images. With less computation and manually tuning, our framework achieves state-of-the-art results.

An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

Cephalometric tracing method is usually used in orthodontic diagnosis and treatment planning. In this paper, we propose a deep learning based framework to automatically detect anatomical landmarks in cephalometric X-ray images. We train the deep encoder-decoder model for landmark detection, which combines global landmark configuration with local high-resolution feature responses. The proposed framework is based on a 2-stage u-net, regressing the multi-channel heatmaps for landmark detection. In this framework, we embed attention mechanism with global stage heatmaps, guiding the local stage inferring, to regress the local heatmap patches in a high resolution. Besides, an Expansive Exploration strategy is applied to improve robustness while inferring, expanding the searching scope without increasing model complexity. We have evaluated the proposed framework in the most widely-used public dataset of landmark detection in cephalometric X-ray images. With less computation and manually tuning, the proposed framework achieves state-of-the-art results.

Benefiting from the strong capabilities of deep CNNs for feature representation and nonlinear mapping, deep-learning-based methods have achieved excellent performance in single image super-resolution. However, most existing SR methods depend on the high capacity of networks which is initially designed for visual recognition, and rarely consider the initial intention of super-resolution for detail fidelity. Aiming at pursuing this intention, there are two challenging issues to be solved: (1) learning appropriate operators which is adaptive to the diverse characteristics of smoothes and details; (2) improving the ability of model to preserve the low-frequency smoothes and reconstruct the high-frequency details. To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields. Particularly, we propose a Hessian filtering for interpretable feature representation which is high-profile for detail inference, a dilated encoder-decoder and a distribution alignment cell to improve the inferred Hessian features in morphological manner and statistical manner respectively. Extensive experiments demonstrate that the proposed methods achieve superior performances over the state-of-the-art methods quantitatively and qualitatively. Code is available at this https URL.

Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution.

In the field of data mining, it is often encountered to perform cluster analysis on large data sets with mixed numeric and categorical values. However, most exciting clustering algorithms are only efficient for the numeric data rather than the mixed data set. For this purpose, this paper presents a novel clustering algorithm for these mixed data sets by modifying the common cost function, trace of the within cluster dispersion matrix. The genetic algorithm (GA) is used to optimize the new cost function to obtain valid clustering result. Experimental result illustrates that the GA-based new clustering algorithm is feasible for the large data sets with mixed numeric and categorical values.

Jie Li

Papers

Robust tensor subspace learning for anomaly detection

An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution.

A GA-based clustering algorithm for large data sets with mixed numeric and categorical values