Online Deep Clustering for Unsupervised 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.

CURL: Image Classification using co-training and Unsupervised Representation 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

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

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.

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.

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.

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.

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.

Our goal is to evaluate the usefulness of unsupervised representation learning techniques for detecting stances of Fake News. Therefore we examine several pre-trained language models with respect to their performance on two Fake News related data sets, both consisting of instances with a headline, an associated news article and the stance of the article towards the respective headline. Specifically, the aim is to understand how much hyperparameter tuning is necessary when fine-tuning the pre-trained architectures, how well transfer learning works in this specific case of stance detection and how sensitive the models are to changes in hyperparameters like batch size, learning rate (schedule), sequence length as well as the freezing technique. The results indicate that the computationally more expensive autoregression approach of XLNet (Yanget al., 2019) is outperformed by BERT-based models, notably by RoBERTa (Liu et al., 2019).While the learning rate seems to be the most important hyperparameter, experiments with different freezing techniques indicate that all evaluated architectures had already learned powerful language representations that pose a good starting point for fine-tuning them.

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.

While self-supervised graph pretraining techniques have shown promising results in various domains, their application still experiences challenges of limited topology learning, human knowledge dependency, and incompetent multi-level interactions. To address these issues, we propose a novel solution, Dual-level Graph self-supervised Pretraining with Motif discovery (DGPM), which introduces a unique dual-level pretraining structure that orchestrates node-level and subgraph-level pretext tasks. Unlike prior approaches, DGPM autonomously uncovers significant graph motifs through an edge pooling module, aligning learned motif similarities with graph kernel-based similarities. A cross-matching task enables sophisticated node-motif interactions and novel representation learning. Extensive experiments on 15 datasets validate DGPM's effectiveness and generalizability, outperforming state-of-the-art methods in unsupervised representation learning and transfer learning settings. The autonomously discovered motifs demonstrate the potential of DGPM to enhance robustness and interpretability.

Self-supervised learning is a promising unsupervised learning framework that has achieved success with large floating point networks. But such networks are not readily deployable to edge devices. To accelerate deployment of models with the benefit of unsupervised representation learning to such resource limited devices for various downstream tasks, we propose a self-supervised learning method for binary networks that uses a moving target network. In particular, we propose to Jointly train a randomly initialized classifier, attached to a pretrained floating point feature extractor, with a binary network. Additionally, we propose a feature similarity loss, a dynamic loss balancing and modified multi-stage training to further improve the accuracy, and call our method BURN. Our empirical validations over five downstream tasks using seven datasets show that BURN outperforms self-supervised baselines for binary networks and sometimes outperforms supervised pretraining. Code is availabe at https://github.com/naver-ai/burn.