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

비만아 부모의 돌봄 경험: q 방법론

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

Ensemble methods are considered the state‐of‐the art solution for many machine learning challenges. Such methods improve the predictive performance of a single model by training multiple models and combining their predictions. This paper introduce the concept of ensemble learning, reviews traditional, novel and state‐of‐the‐art ensemble methods and discusses current challenges and trends in the field.

Ensemble learning: A survey

The need for appropriate ways to measure the distance or similarity between data is ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such good metrics for specific problems is generally difficult. This has led to the emergence of metric learning, which aims at automatically learning a metric from data and has attracted a lot of interest in machine learning and related fields for the past ten years. This survey paper proposes a systematic review of the metric learning literature, highlighting the pros and cons of each approach. We pay particular attention to Mahalanobis distance metric learning, a well-studied and successful framework, but additionally present a wide range of methods that have recently emerged as powerful alternatives, including nonlinear metric learning, similarity learning and local metric learning. Recent trends and extensions, such as semi-supervised metric learning, metric learning for histogram data and the derivation of generalization guarantees, are also covered. Finally, this survey addresses metric learning for structured data, in particular edit distance learning, and attempts to give an overview of the remaining challenges in metric learning for the years to come.

A Survey on Metric Learning for Feature Vectors and Structured Data

Face image-sketch synthesis via generative adversarial fusion

In recent years, researchers have proposed many deep learning algorithms for data representation learning. However, most deep networks require extensive training data and a lot of training time to obtain good results. In this paper, we propose a novel deep learning method based on stretching deep architectures that are composed of stacked feature learning models. Hence, the method is called “stretching deep architectures” (SDA). In the feedforward propagation of SDA, feature learning models are firstly stacked and learned layer by layer, and then the stretching technique is applied to map the last layer of the features to a high-dimensional space. Since the feature learning models are optimized effectively, and the stretching technique can be easily calculated, the training of SDA is very fast. More importantly, the learning of SDA does not need back-propagation optimization, which is quite different from most of the existing deep learning models. We have tested SDA in visual texture perception, handwritten text recognition, and natural image classification applications. Extensive experiments demonstrate the advantages of SDA over traditional feature learning models and related deep learning models.

/pdf/stretching-deep-architectures-a-deep-learning-method-without-3h6mfsx4.pdf

Stretching Deep Architectures: A Deep Learning Method without Back-Propagation Optimization

Mining the intrinsic information of sequential data to predict the future data has a promising research prospect. Considering the temporal features of sequential data, existing approaches generally adopt recurrent neural network and its variants for the prediction. However, for sequences with complex structure, such as video frame sequence, these approaches cannot guarantee to obtain promising prediction results. In this paper, to address the above issue, we propose a novel architecture, called recurrent adversarial video prediction network (RAVPN), which can not only extract the temporal and spatial features of video sequences, but also optimize the generator and discriminator based on the adversarial strategy. Specifically, we use sliding windows with length t +1 and set the (t + 1)-th frame as the label of its previous t frames. The generator takes the first t frames as input and tries to generate the (t + 1)-th frame, while the discriminator distinguishes whether a sample is real or fake to boost the performance of the generator. Experimental results show that our novel RAVPN can obtain a promising performance on video prediction tasks compared with other deep sequence prediction models.

Recurrent Adversarial Video Prediction Network

With the advancements in rising computer vision processing, Transformer has attracted increasing interesting in this field. However, it is limited because of its unprecedented storage, heavy reliance on data size and intolerable computational power consumption. While lightweight network is in other extreme, pursuing the compact architectures accompanied by performance loss. In this paper, we enhance an architecture as the backbone of object detection networks through combining right-size Transformer, i.e. Vision Transformer module. Specifically, based on GhostNet, a well-known lightweight neural network structure moreover, embed this Vision Transformer module at the end of GhostNet, and use the input data with slicing design to reduce the computational burden of the neural networks. Vision Transformer is taken to enhance the architecture as the backbone of object detection networks, and the well-known YOLOv5 as the baseline. We conduct multi-metric comparison experiments on two medium-scale object detection datasets with large, medium and small scale networks. Results show that without relying on ultra-large dataset and pre-trained models, the proposed Transformer module enhanced architecture achieves comparable or even higher mAP metrics with only half of the model size and floating-point computation of the baseline.

A Compact Object Detection Architecture with Transformer Enhancing

Perceptual features, for example direction, contrast and repetitiveness, are important visual factors for human to perceive a texture. However, it needs to perform psychophysical experiment to quantify these perceptual features’ scale, which requires a large amount of human labor and time. This paper focuses on the task of obtaining perceptual features’ scale of textures by small number of textures with perceptual scales through a rating psychophysical experiment (what we call labeled textures) and a mass of unlabeled textures. This is the scenario that the semi-supervised learning is naturally suitable for. This is meaningful for texture perception research, and really helpful for the perceptual texture database expansion. A graph-based semi-supervised learning method called random multi-graphs, RMG for short, is proposed to deal with this task. We evaluate different kinds of features including LBP, Gabor, and a kind of unsupervised deep features extracted by a PCA-based deep network. The experimental results show that our method can achieve satisfactory effects no matter what kind of texture features are used.

Guoqiang Zhong

Papers

Face image-sketch synthesis via generative adversarial fusion

Stretching Deep Architectures: A Deep Learning Method without Back-Propagation Optimization

Recurrent Adversarial Video Prediction Network

A Compact Object Detection Architecture with Transformer Enhancing

Visual texture perception via graph-based semi-supervised learning