Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning

Sleep staging based on electroencephalogram (EEG) signal, as one of the vital bases of study on sleep diagnosis, has been under massive attention. With the spring up of deep learning these years, the idea of combining deep learning structure with automatic sleep staging has been an attractive topic. However, the labeling of sleep stages requires professional knowledge as well as plenty of time, which raise the barrier to evaluate this idea. In this study, the method of unsupervised feature learning based on a mass of unlabeled data and a small number of labeled data was proposed to accomplish sleep staging. The unsupervised feature learning structure was built based on a pair of symmetric convolutional neural networks, with the help of a shallow neural network classifier to classify sleep stages. The results showed that under the condition of the very few labeled data, sleep staging based on unsupervised feature learning can achieve similar accuracy to supervised feature learning, which provides a new direction for the application of deep learning method in dealing with data that is difficult to label or lack of prior knowledge.

Recognizing Human action in video is an very active research topic. There are a growing variety of human action datasets with different video length, different practitioners. Make human action recognition becomes a very difficult topic. A majority researchers solve the problem by extracting key frames from the videos. Most paper use feature Clustering methods to extract key frames in videos. On one hand, the large variety of visual content in videos make handcraft feature isn't effective enough, since there are no fixed descriptors can describe all video cases. On the other hand, traditional clustering algorithms are easily influenced by the choice of initial clustering centers. An Unsupervised feature learning and clustering method for key frame extraction is proposed in this paper, which can be used for human action recognition. Stacked auto-encoder(SAE) is trained using videos from 10 different human actions, SAE is used as a feature extractor to learn features representing human actions. Affinity Propagation Clustering algorithm is used to select key frames from video sequences. We use a variety of videos to do the experiments. Experiments demonstrate that our method can be effectively summarizing video shots considering different human actions.

Extreme learning machine (ELM) as well as its variants have been widely used in many fields for its good generalization performance and fast learning speed. Though distributed ELM can sufficiently process large-scale labeled training data, the current technology is not able to process partial labeled or unlabeled training data. Therefore, we propose a new unified distributed ELM with supervised, semi-supervised and unsupervised learning based on MapReduce framework, called U-DELM. The U-DELM method can be used to overcome the existing distributed ELM framework’s lack of ability to process partially labeled and unlabeled training data. We first compare the computation formulas of supervised, semi-supervised and unsupervised learning methods and found that the majority of expensive computations are decomposable. Next, MapReduce framework based U-DELM is proposed, which extracts three different matrices continued multiplications from the three computational formulas introduced above. After that, we transform the cumulative sums respectively to make them suitable for MapReduce. Then, the combination of the three computational formulas are used to solve the output weight in three different learning methods. Finally, by using benchmark and synthetic datasets, we are able to test and verify the efficiency and effectiveness of U-DELM on learning massive data. Results prove that U-DELM can achieve unified distribution on supervised, semi-supervised and unsupervised learning.

Artificial Intelligence (AI) has advanced in a rapid and exponential manner and AI is now revolutionizing the medical field, the development of self-driving cars, and the management of financial operations. A major reason for such achievement is the efficiency and performance of AI models, which can be drastically boosted through new learning methods. One of the most promising avenues is the unsupervised representation learning method that also offers the choice of leaping over the traditional supervised learning. Instead of supervised learning, where labeled data is the base upon which training of models takes place, unsupervised learning allows AI systems to get new insights out of raw, unlabeled data without any human intervention. This method teaches the AI system how to represent the data in an organized manner, thus enabling it to uncover hidden features and relations without anyone helping it. In effect, AI models, powered by unsupervised representation learning, can be quite successful in areas like clustering, anomaly detection, and feature extraction, frequently beating traditional methods in terms of their speed and accuracy. .The skill of finding deep structures in a dataset can unexpectedly influence many areas of the sciences, e.g., it can help us create a better diagnostic system in medicine or use it for decision-making when investing in the stock market

Predicting and Grouping Digitized Paintings by Style using Unsupervised Feature Learning.

Efficient modeling of high-dimensional data requires extracting only relevant dimensions through feature learning. Unsupervised feature learning has gained tremendous attention due to its unbiased approach, no need for prior knowledge or expensive manual processing, and ability to handle exponential data growth. Deep Autoencoder (AE) is a state-of-the-art deep neural network for unsupervised feature learning, which learns embedded-representations using a series of stacked layers. However, as the AE network gets deeper, these learned embedded-representations can deteriorate due to vanishing gradient, leading to performance degradation. This article presents ResNet Autoencoder (RAE) and its convolutional version (C-RAE) for unsupervised feature learning. The advantage of RAE and C-RAE is that it enables the user to add residual connections for increased network capacity without incurring the cost of degradation for unsupervised feature learning compared to standard AEs. While RAE and C-RAE inherit all the advantages of AEs, such as automated non-linear feature extraction and unsupervised learning, they also allow users to design larger networks without adverse effects on feature learning performance. We performed classification on learned embedded-representation to evaluate RAE and C-RAE. RAE and C-RAE were compared against AEs on MNIST, Fashion MNIST, and CIFAR10 datasets. When increasing the number of layers, C-RAE outperformed AE by showing significantly lower performance degradation of classification accuracy (less than 3%) compared to AE (33% to 65%). Further, C-RAE exhibited higher mean accuracy and lower variance of accuracy than standard AE. When comparing RAE and C-RAE with widely used feature learning methods (Convolutional AE, PCA, ICA, LLE, Factor Analysis, and SVD), C-RAE showed the highest accuracy.

For computer vision based appraoches such as image classification (Krizhevsky et al. 2012), object detection (Ren et al. 2015) or pixel-wise weed classification (Milioto et al. 2017) machine learning is used for both feature extraction and processing (e.g. classification or regression). Historically, feature extraction (e.g. PCA; Ch. 12.1. in Bishop 2006) and processing were sequential and independent tasks (Wöber et al. 2013). Since the rise of convolutional neuronal networks (LeCun et al. 1989), a deep machine learning approach optimized for images, in 2012 (Krizhevsky et al. 2012), feature extraction for image analysis became an automated procedure. A convolutional neuronal net uses a deep architecture of artificial neurons (Goodfellow 2016) for both feature extraction and processing. Based on prior information such as image classes and supervised learning procedures, parameters of the neuronal nets are adjusted. This is known as the learning process. Simultaneously, geometric morphometrics (Tibihika et al. 2018, Cadrin and Friedland 1999) are used in biodiversity research for association analysis. Those approaches use deterministic two-dimensional locations on digital images (landmarks; Mitteroecker et al. 2013), where each position corresponds to biologically relevant regions of interest. Since this methodology is based on scientific results and compresses image content into deterministic landmarks, no uncertainty regarding those landmark positions is taken into account, which leads to information loss (Pearl 1988). Both, the reduction of this loss and novel knowledge detection, can be done using machine learning. Supervised learning methods (e.g., neuronal nets or support vector machines (Ch. 5 and 6. in Bishop 2006)) map data on prior information (e.g. labels). This increases the performance of classification or regression but affects the latent representation of the data itself. Unsupervised learning (e.g. latent variable models) uses assumptions concerning data structures to extract latent representations without prior information. Those representations does not have to be useful for data processing such as classification and due to that, the use of supervised and unsupervised machine learning and combinations of both, needs to be chosen carefully, according to the application and data. In this work, we discuss unsupervised learning algorithms in terms of explainability, performance and theoretical restrictions in context of known deep learning restrictions (Marcus 2018, Szegedy et al. 2014, Su et al. 2017). We analyse extracted features based on multiple image datasets and discuss shortcomings and performance for processing (e.g. reconstruction error or complexity measurement (Pincus 1997)) using the principal component analysis (Wöber et al. 2013), independent component analysis (Stone 2004), deep neuronal nets (auto encoders; Ch. 14 in Goodfellow 2016) and Gaussian process latent variable models (Titsias and Lawrence 2010, Lawrence 2005).

Establishing accurate anatomical correspondences is critical for medical image registration. Although many hand-engineered features have been proposed for correspondence detection in various registration applications, no features are general enough to work well for all image data. Although many learning-based methods have been developed to help selection of best features for guiding correspondence detection across subjects with large anatomical variations, they are often limited by requiring the known correspondences (often presumably estimated by certain registration methods) as the ground truth for training. To address this limitation, we propose using an unsupervised deep learning approach to directly learn the basis filters that can effectively represent all observed image patches. Then, the coefficients by these learnt basis filters in representing the particular image patch can be regarded as the morphological signature for correspondence detection during image registration. Specifically, a stacked two-layer convolutional network is constructed to seek for the hierarchical representations for each image patch, where the high-level features are inferred from the responses of the low-level network. By replacing the hand-engineered features with our learnt data-adaptive features for image registration, we achieve promising registration results, which demonstrates that a general approach can be built to improve image registration by using data-adaptive features through unsupervised deep learning.

Learning feature embedding directly from images without any human supervision is a very challenging and essential task in the field of computer vision and machine learning. Following the paradigm in supervised manner, most existing unsupervised metric learning approaches mainly focus on binary similarity in Euclidean space. However, these methods cannot achieve promising performance in many practical applications, where the manual information is lacking and data exhibits non-Euclidean latent anatomy. To address this limitation, we propose an Unsupervised Hyperbolic Metric Learning method with Hierarchical Similarity. It considers the natural hierarchies of data by taking advantage of Hyperbolic metric learning and hierarchical clustering, which can effectively excavate richer similarity information beyond binary in modeling. More importantly, we design a new loss function to capture the hierarchical similarity among samples to enhance the stability of the proposed method. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current unsupervised deep metric learning approaches.

Unsupervised learning from EEG data for epilepsy: A systematic literature review.

Despite recent advances in the field of supervised deep learning for text line segmentation, unsupervised deep learning solutions are beginning to gain popularity. In this paper, we present an unsupervised deep learning method that embeds document image patches to a compact Euclidean space where distances correspond to a coarse text line pattern similarity. Once this space has been produced, text line segmentation can be easily implemented using standard techniques with the embedded feature vectors. To train the model, we extract random pairs of document image patches with the assumption that neighbour patches contain a similar coarse trend of text lines, whereas if one of them is rotated, they contain different coarse trends of text lines. Doing well on this task requires the model to learn to recognize the text lines and their salient parts. The benefit of our approach is zero manual labelling effort. We evaluate the method qualitatively and quantitatively on several variants of text line segmentation datasets to demonstrate its effectivity.

Machine learning has significantly impacted the analysis of biological images and is now an important part of many biological data analysis pipelines. A variety of biological and biomedical domain-related tasks is gaining benefit from image analysis and pattern recognition tools developed currently. Applications include diagnostic histopathology, environmental monitoring, synthetic biology, genomics, and proteomics. Particularly in the last decade, several deep learning and advanced computer vision methods such as convolutional neural networks (CNNs), typically trained in a supervised fashion, have started to be largely employed in biological image classification. Moreover, the advancement of automatic acquisition systems has been generating a massive amount of biological data, which requires to be analyzed by domain experts. However, the cost of manual annotation of such data has become a bottleneck, impairing the application of supervised machine learning algorithms. Biological images generally have an intrinsic high variability, whose identity is sometimes hard to assign and strongly dependent on the annotator’s expertise. In this context, a limited number of annotation-free (i.e., unsupervised) learning solutions have been proposed, typically based on hand-crafted features, specifically tailored for a certain biological domain. Nonetheless, a successful unsupervised learning approach must be accurate, and sufficiently robust to deal with different biological domains. This paper aims at providing a viable solution to these issues, proposing an unsupervised learning algorithm based on compressed deep features for image classification. We exploit features extracted from ImageNet pre-trained transformers and CNNs, further compressed with a customized β-Variational AutoEncoder (β-VAE), that we call reconstruction VAE (R-VAE). We test our algorithm on biological images coming from diverse domains characterized by high variability in shape and texture information and acquired with widely differing imaging platforms. Considered image datasets range from multi-cellular organisms (plankton, coral) to sub-cellular organelles (budding yeast vacuoles, human cells’ nuclei, etc.). Our results show that the compressed deep features extracted from different pre-trained vision models establish new unsupervised learning state-of-the-art performances for the investigated datasets.

Seismic data denoising is a critical component of seismic data processing, yet effectively removing erratic noise, characterized by its non-Gaussian distribution and high amplitude, remains a substantial challenge for conventional methods and deep-learning (DL) algorithms. Supervised learning frameworks typically outperform others, but they require pairs of noisy data sets alongside corresponding clean ground truth, which is impractical for real-world seismic data sets. In contrast, unsupervised learning (UL) methods, which do not rely on ground truth during training, often fall short in performance when compared with their supervised or traditional denoising counterparts. Moreover, current unsupervised DL methods fail to address the specific challenges posed by erratic seismic noise adequately. This paper introduces a novel zero-shot unsupervised DL framework designed specifically to mitigate random and erratic noise, with a particular emphasis on blended noise. Drawing inspiration from Noise2Noise (N2N) and data augmentation principles, we develop a robust self-supervised denoising network called robust Noiser2Noiser. Our approach eliminates the need for paired noisy and clean data sets as required by supervised methods or paired noisy data sets as in N2N. Instead, our framework relies solely on the original noisy seismic data set. Our methodology generates two independent recorrupted data sets from the original noisy data set, using one as the input and the other as the training target. Subsequently, we use a DL-based denoiser, denoising convolutional neural network, for training purposes. To address various types of random and erratic noise, the original noisy data set is recorrupted with the same noise type. Detailed explanations for generating training input and target data for blended data are provided. We apply our network to synthetic and real marine data examples, demonstrating significantly improved noise attenuation performance compared with traditional denoising methods and state-of-the-art UL Codes are available on https://github.com/Ji-seismic/N2N_deblending.

This article proposes an unsupervised deep learning–based approach to detect structural damage. Supervised deep learning methods have been proposed in recent years, but they require data from an intact structure and various damage scenarios of monitored structures for their training processes. However, the labeling work on the training data is typically time-consuming and costly, and sometimes collecting sufficient training data from various damage scenarios of infrastructures in service is impractical. In this article, the proposed unsupervised deep learning method based on a deep auto-encoder with an one-class support vector machine only uses the measured acceleration response data acquired from intact or baseline structures as training data, which enables future structural damage to be detected. The major contributions and novelties of the proposed method are as follows. First, an appropriate deep auto-encoder is carefully designed through comparative studies on the depth of neural networks. Second, the designed deep auto-encoder is taken as an extractor to obtain damage-sensitive features from the measured acceleration response data, and an one-class support vector machine is used as a damage detector. Third, experimental and numerical studies validate the high accuracy of the proposed method for damage detection: a 97.4% mean average for a 12-story numerical building model and a 91.0% accuracy for a laboratory-scaled steel bridge. Fourth, the proposed method also detects light damage (i.e. a 10% reduction in stiffness) with 96.9% to 99.0% accuracy, which shows its superior performance compared with the current state of the art. Fifth, it provides stable and more robust damage detection performance with reduced tuning parameters.

In recent years, feature learning methods based on unsupervised learning get more and more attention.Until now, Unsupervised feature learning has been applied to solve many problems such as detection, recognition and classification.In this paper, we propose a deep feature learning method based on Sparse AutoEncoder to recognize vehicle types and to improve the classification accuracy rate.First we used Sparse AutoEncoder to generate the convolutional kernel and used the convolutional kernel to generate convolutional feature.Then pooling was applied.We repeated the network several times to construct a deep feature learning framework.To improve performance, we also combined the feature learned in different layer to form a new feature vector and applied PCA to reduce the dimension.Finally we used softmax to recognize the vehicle type.Adopting the local receive field, we can reduce the parameters.The experiment shows that our method can improve the performance a little.