Momentum Contrast for Unsupervised Visual Representation Learning

Local discriminative representation is needed in many medical image analysis tasks such as identifying sub-types of lesion or segmenting detailed components of anatomical structures. However, the commonly applied supervised representation learning methods require a large amount of annotated data, and unsupervised discriminative representation learning distinguishes different images by learning a global feature, both of which are not suitable for localized medical image analysis tasks. In order to avoid the limitations of these two methods, we introduce local discrimination into unsupervised representation learning in this work. The model contains two branches: one is an embedding branch which learns an embedding function to disperse dissimilar pixels over a low-dimensional hypersphere; and the other is a clustering branch which learns a clustering function to classify similar pixels into the same cluster. These two branches are trained simultaneously in a mutually beneficial pattern, and the learnt local discriminative representations are able to well measure the similarity of local image regions. These representations can be transferred to enhance various downstream tasks. Meanwhile, they can also be applied to cluster anatomical structures from unlabeled medical images under the guidance of topological priors from simulation or other structures with similar topological characteristics. The effectiveness and usefulness of the proposed method are demonstrated by enhancing various downstream tasks and clustering anatomical structures in retinal images and chest X-ray images.KeywordsUnsupervised representation learningLocal discriminationTopological priors

In real-world applications, clustering or classification can usually be improved by fusing information from different views. Therefore, unsupervised representation learning on multi-view data becomes a compelling topic in machine learning. In this paper, we propose a novel and flexible unsupervised multi-view representation learning model termed Collaborative Multi-View Information Bottleneck Networks (CMIB-Nets), which comprehensively explores the common latent structure and the view-specific intrinsic information, and discards the superfluous information in the data significantly improving the generalization capability of the model. Specifically, our proposed model relies on the information bottleneck principle to integrate the shared representation among different views and the view-specific representation of each view, prompting the multi-view complete representation and flexibly balancing the complementarity and consistency among multiple views. We conduct extensive experiments (including clustering analysis, robustness experiment, and ablation study) on real-world datasets, which empirically show promising generalization ability and robustness compared to state-of-the-arts.

Developing the utilized intelligent systems is increasingly important to learn effective text representations, especially extract the sentence features. Numerous previous studies have been concentrated on the task of sentence representation learning based on deep learning approaches. However, the present approaches are mostly proposed with the single task or replied on the labeled corpus when learning the embedding of the sentences. In this paper, we assess the factors in learning sentence representation and propose an efficient unsupervised learning framework with multi-task learning (USR-MTL), in which various text learning tasks are merged into the unitized framework. With the syntactic and semantic features of sentences, three different factors to some extent are reflected in the task of the sentence representation learning that is the wording, or the ordering of the neighbored sentences of a target sentence in other words. Hence, we integrate the word-order learning task, word prediction task, and the sentence-order learning task into the proposed framework to attain meaningful sentence embeddings. Here, the process of sentence embedding learning is reformulated as a multi-task learning framework of the sentence-level task and the two word-level tasks. Moreover, the proposed framework is motivated by an unsupervised learning algorithm utilizing the unlabeled corpus. Based on the experimental results, our approach achieves the state-of-the-art performances on the downstream natural language processing tasks compared to the popular unsupervised representation learning techniques. The experiments on representation visualization and task analysis demonstrate the effectiveness of the tasks in the proposed framework in creating reasonable sentence representations proving the capacity of the proposed unsupervised multi-task framework for the sentence representation learning.

Adversarial correlated autoencoder for unsupervised multi-view representation learning

Learning data representations directly from the data itself is an approach that has shown great success in different pattern recognition problems, outperforming state-of-the-art feature extraction schemes for different tasks in computer vision, speech recognition and natural language processing. Representation learning applies unsupervised and supervised machine learning methods to large amounts of data to find building-blocks that better represent the information in it. Digitized histopathology images represents a very good testbed for representation learning since it involves large amounts of high complex, visual data. This paper presents a comparative evaluation of different supervised and unsupervised representation learning architectures to specifically address open questions on what type of learning architectures (deep or shallow), type of learning (unsupervised or supervised) is optimal. In this paper we limit ourselves to addressing these questions in the context of distinguishing between anaplastic and non-anaplastic medulloblastomas from routine haematoxylin and eosin stained images. The unsupervised approaches evaluated were sparse autoencoders and topographic reconstruct independent component analysis, and the supervised approach was convolutional neural networks. Experimental results show that shallow architectures with more neurons are better than deeper architectures without taking into account local space invariances and that topographic constraints provide useful invariant features in scale and rotations for efficient tumor differentiation.

CURL: Image Classification using co-training and Unsupervised Representation Learning

Unsupervised and self-supervised representation learning has become popular in recent years for learning useful features from unlabelled data. Representation learning has been mostly developed in the neural network literature, and other models for representation learning are surprisingly unexplored. In this work, we introduce and analyze several kernel-based representation learning approaches: Firstly, we define two kernel Self-Supervised Learning (SSL) models using contrastive loss functions and secondly, a Kernel Autoencoder (AE) model based on the idea of embedding and reconstructing data. We argue that the classical representer theorems for supervised kernel machines are not always applicable for (self-supervised) representation learning, and present new representer theorems, which show that the representations learned by our kernel models can be expressed in terms of kernel matrices. We further derive generalisation error bounds for representation learning with kernel SSL and AE, and empirically evaluate the performance of these methods in both small data regimes as well as in comparison with neural network based models.

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

There has been a growing focus on the use of artificial intelligence and machine learning for affective computing to further enhance user experience through emotion recognition. Typically, machine learning models used for affective computing are trained using manually extracted features from biological signals. Such features may not generalize well for large datasets. One approach to address this issue is to use fully supervised deep learning methods to learn latent representations. However, this method requires human supervision to label the data, which may be unavailable. In this work we propose an unsupervised framework for representation learning. The proposed framework utilizes two stacked convolutional autoencoders to learn latent representations from wearable electrocardiogram and electrodermal activity signals. The representations learned from this unsupervised framework are subsequently utilized within a random forest model to classify arousal. To validate this framework, an aggregation of the AMIGOS, ASCERTAIN, CLEAS, and MAHNOB-HCI datasets is created. The results of our proposed method are compared with other methods including convolutional neural networks, as well as methods that employ manual extraction of features. We show that our method outperforms current state-of-the-art results. The results show the wide-spread applicability for stacked convolutional autoencoders to be used for affective computing.

Semantically consistent multi-view representation learning

Recent studies have revealed that GNNs are vulnerable to adversarial attacks. Most existing robust graph learning methods measure model robustness based on label information, rendering them infeasible when label information is not available. A straightforward direction is to employ the widely used Infomax technique from typical Unsupervised Graph Representation Learning (UGRL) to learn robust unsupervised representations. Nonetheless, directly transplanting the Infomax technique from typical UGRL to robust UGRL may involve a biased assumption. In light of the limitation of Infomax, we propose a novel unbiased robust UGRL method called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Robust Graph Information Bottleneck</i> (RGIB), which is grounded in the Information Bottleneck (IB) principle. Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph. There are mainly two challenges to optimizing RGIB: 1) high complexity of adversarial attack to perturb node features and graph structure jointly in the training procedure; 2) mutual information estimation upon adversarially attacked graphs. To tackle these problems, we further propose an efficient adversarial training strategy with only feature perturbations and an effective mutual information estimator with the subgraph-level summary. Moreover, we theoretically establish a connection between our proposed RGIB and the robustness of downstream classifiers, revealing that RGIB can provide a lower bound on the adversarial risk of downstream classifiers. Extensive experiments over several benchmarks and downstream tasks demonstrate the effectiveness and superiority of our proposed method.

Semi-supervised temporal action segmentation (SS-TAS) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive learning in unsupervised representation learning using unlabelled data. However, learning the representation of each frame by unsupervised contrastive learning for action segmentation remains an open and challenging problem. In this paper, we propose a novel Semantic-guided Multi-level Contrast scheme with a Neighbourhood-Consistency-Aware unit (SMC-NCA) to extract strong frame-wise representations for SS-TAS. Specifically, for representation learning, SMC is first used to explore intra- and inter-information variations in a unified and contrastive way, based on action-specific semantic information and temporal information highlighting relations between actions. Then, the NCA module, which is responsible for enforcing spatial consistency between neighbourhoods centered at different frames to alleviate over-segmentation issues, works alongside SMC for semi-supervised learning (SSL). Our SMC outperforms the other state-of-the-art methods on three benchmarks, offering improvements of up to 17.8<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 12.6<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> in terms of Edit distance and accuracy, respectively. Additionally, the NCA unit results in significantly better segmentation performance in the presence of only 5<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> labelled videos. We also demonstrate the generalizability and effectiveness of the proposed method on our Parkinson's Disease Mouse Behaviour (PDMB) dataset.

With the successful application of deep learning to magnetic resonance (MR) imaging, parallel imaging techniques based on neural networks have attracted wide attention. However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited. And the interpretability of models is not strong enough. To tackle this issue, this paper proposes a Physics-bAsed unsupeRvised Contrastive rEpresentation Learning (PARCEL) method to speed up parallel MR imaging. Specifically, PARCEL has a parallel framework to contrastively learn two branches of model-based unrolling networks from augmented undersampled multi-coil k-space data. A sophisticated co-training loss with three essential components has been designed to guide the two networks in capturing the inherent features and representations for MR images. And the final MR image is reconstructed with the trained contrastive networks. PARCEL was evaluated on two vivo datasets and compared to five state-of-the-art methods. The results show that PARCEL is able to learn essential representations for accurate MR reconstruction without relying on fully sampled datasets. The code will be made available at https://github.com/ternencewu123/PARCEL.

Graph prototypical contrastive learning

Unsupervised multi-view graph representation learning with dual weight-net