Self-supervised Learning Techniques Research Articles

A Tale of Color Variants: Representation and Self-Supervised Learning in Fashion E-commerce

In this paper, we address a crucial problem in fashion e-commerce (with respect to customer experience, as well as revenue): color variants identification, i.e., identifying fashion products that match exactly in their design (or style), but only to differ in their color. We propose a generic framework, that leverages deep visual Representation Learning at its heart, to address this problem for our fashion e-commerce platform. Our framework could be trained with supervisory signals in the form of triplets, that are obtained manually. However, it is infeasible to obtain manual annotations for the entire huge collection of data usually present in fashion e-commerce platforms, such as ours, while capturing all the difficult corner cases. But, to our rescue, interestingly we observed that this crucial problem in fashion e-commerce could also be solved by simple color jitter based image augmentation, that recently became widely popular in the contrastive Self-Supervised Learning (SSL) literature, that seeks to learn visual representations without using manual labels. This naturally led to a question in our mind: Could we leverage SSL in our use-case, and still obtain comparable performance to our supervised framework? The answer is, Yes! because, color variant fashion objects are nothing but manifestations of a style, in different colors, and a model trained to be invariant to the color (with, or without supervision), should be able to recognize this! This is what the paper further demonstrates, both qualitatively, and quantitatively, while evaluating a couple of state-of-the-art SSL techniques, and also proposing a novel method.

Self-Supervised Object Localization with Joint Graph Partition

Object localization aims to generate a tight bounding box for the target object, which is a challenging problem that has been deeply studied in recent years. Since collecting bounding-box labels is time-consuming and laborious, many researchers focus on weakly supervised object localization (WSOL). As the recent appealing self-supervised learning technique shows its powerful function in visual tasks, in this paper, we take the early attempt to explore unsupervised object localization by self-supervision. Specifically, we adopt different geometric transformations to image and utilize their parameters as pseudo labels for self-supervised learning. Then, the class-agnostic activation map (CAAM) is used to highlight the target object potential regions. However, such attention maps merely focus on the most discriminative part of the objects, which will affect the quality of the predicted bounding box. Based on the motivation that the activation maps of different transformations of the same image should be equivariant, we further design a siamese network that encodes the paired images and propose a joint graph cluster partition mechanism in an unsupervised manner to enhance the object co-occurrent regions. To validate the effectiveness of the proposed method, extensive experiments are conducted on CUB-200-2011, Stanford Cars and FGVC-Aircraft datasets. Experimental results show that our method outperforms state-of-the-art methods using the same level of supervision, even outperforms some weakly-supervised methods.

Deep Learning in Neuroimaging: Overcoming Challenges With Emerging Approaches.

Deep learning (DL) is of great interest in psychiatry due its potential yet largely untapped ability to utilize multidimensional datasets (such as fMRI data) to predict clinical outcomes. Typical DL methods, however, have strong assumptions, such as large datasets and underlying model opaqueness, that are suitable for natural image prediction problems but not medical imaging. Here we describe three relatively novel DL approaches that may help accelerate its incorporation into mainstream psychiatry research and ultimately bring it into the clinic as a prognostic tool. We first introduce two methods that can reduce the amount of training data required to develop accurate models. These may prove invaluable for fMRI-based DL given the time and monetary expense required to acquire neuroimaging data. These methods are (1) transfer learning − the ability of deep learners to incorporate knowledge learned from one data source (e.g., fMRI data from one site) and apply it toward learning from a second data source (e.g., data from another site), and (2) data augmentation (via Mixup) − a self-supervised learning technique in which “virtual” instances are created. We then discuss explainable artificial intelligence (XAI), i.e., tools that reveal what features (and in what combinations) deep learners use to make decisions. XAI can be used to solve the “black box” criticism common in DL and reveal mechanisms that ultimately produce clinical outcomes. We expect these techniques to greatly enhance the applicability of DL in psychiatric research and help reveal novel mechanisms and potential pathways for therapeutic intervention in mental illness.

Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity

While self-supervised learning techniques are often used to mining implicit knowledge from unlabeled data via modeling multiple views, it is unclear how to perform effective representation learning in a complex and inconsistent context. To this end, we propose a methodology, specifically consistency and complementarity network (CoCoNet), which avails of strict global inter-view consistency and local cross-view complementarity preserving regularization to comprehensively learn representations from multiple views. On the global stage, we reckon that the crucial knowledge is implicitly shared among views, and enhancing the encoder to capture such knowledge from data can improve the discriminability of the learned representations. Hence, preserving the global consistency of multiple views ensures the acquisition of common knowledge. CoCoNet aligns the probabilistic distribution of views by utilizing an efficient discrepancy metric measurement based on the generalized sliced Wasserstein distance. Lastly on the local stage, we propose a heuristic complementarity-factor, which joints cross-view discriminative knowledge, and it guides the encoders to learn not only view-wise discriminability but also cross-view complementary information. Theoretically, we provide the information-theoretical-based analyses of our proposed CoCoNet. Empirically, to investigate the improvement gains of our approach, we conduct adequate experimental validations, which demonstrate that CoCoNet outperforms the state-of-the-art self-supervised methods by a significant margin proves that such implicit consistency and complementarity preserving regularization can enhance the discriminability of latent representations.

Graph Self-Supervised Learning: A Survey

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field.

Efficient Self-supervised Learning Techniques for Lightweight Depth Completion

Efficient Self-supervised Learning Techniques for Lightweight Depth Completion

Multi-Modal Pain Intensity Assessment Based on Physiological Signals: A Deep Learning Perspective.

Traditional pain assessment approaches ranging from self-reporting methods, to observational scales, rely on the ability of an individual to accurately assess and successfully report observed or experienced pain episodes. Automatic pain assessment tools are therefore more than desirable in cases where this specific ability is negatively affected by various psycho-physiological dispositions, as well as distinct physical traits such as in the case of professional athletes, who usually have a higher pain tolerance as regular individuals. Hence, several approaches have been proposed during the past decades for the implementation of an autonomous and effective pain assessment system. These approaches range from more conventional supervised and semi-supervised learning techniques applied on a set of carefully hand-designed feature representations, to deep neural networks applied on preprocessed signals. Some of the most prominent advantages of deep neural networks are the ability to automatically learn relevant features, as well as the inherent adaptability of trained deep neural networks to related inference tasks. Yet, some significant drawbacks such as requiring large amounts of data to train deep models and over-fitting remain. Both of these problems are especially relevant in pain intensity assessment, where labeled data is scarce and generalization is of utmost importance. In the following work we address these shortcomings by introducing several novel multi-modal deep learning approaches (characterized by specific supervised, as well as self-supervised learning techniques) for the assessment of pain intensity based on measurable bio-physiological data. While the proposed supervised deep learning approach is able to attain state-of-the-art inference performances, our self-supervised approach is able to significantly improve the data efficiency of the proposed architecture by automatically generating physiological data and simultaneously performing a fine-tuning of the architecture, which has been previously trained on a significantly smaller amount of data.

A Deep Learning Model with Self-Supervised Learning and Attention Mechanism for COVID-19 Diagnosis Using Chest X-ray Images

The SARS-CoV-2 virus has spread worldwide, and the World Health Organization has declared COVID-19 pandemic, proclaiming that the entire world must overcome it together. The chest X-ray and computed tomography datasets of individuals with COVID-19 remain limited, which can cause lower performance of deep learning model. In this study, we developed a model for the diagnosis of COVID-19 by solving the classification problem using a self-supervised learning technique with a convolution attention module. Self-supervised learning using a U-shaped convolutional neural network model combined with a convolution block attention module (CBAM) using over 100,000 chest X-Ray images with structure similarity (SSIM) index captures image representations extremely well. The system we proposed consists of fine-tuning the weights of the encoder after a self-supervised learning pretext task, interpreting the chest X-ray representation in the encoder using convolutional layers, and diagnosing the chest X-ray image as the classification model. Additionally, considering the CBAM further improves the averaged accuracy of 98.6%, thereby outperforming the baseline model (97.8%) by 0.8%. The proposed model classifies the three classes of normal, pneumonia, and COVID-19 extremely accurately, along with other metrics such as specificity and sensitivity that are similar to accuracy. The average area under the curve (AUC) is 0.994 in the COVID-19 class, indicating that our proposed model exhibits outstanding classification performance.

Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation

Human perceives rich auditory experience with distinct sound heard by ears. Videos recorded with binaural audio particular simulate how human receives ambient sound. However, a large number of videos are with monaural audio only, which would degrade the user experience due to the lack of ambient information. To address this issue, we propose an audio spatialization framework to convert a monaural video into a binaural one exploiting the relationship across audio and visual components. By preserving the left-right consistency in both audio and visual modalities, our learning strategy can be viewed as a self-supervised learning technique, and alleviates the dependency on a large amount of video data with ground truth binaural audio data during training. Experiments on benchmark datasets confirm the effectiveness of our proposed framework in both semi-supervised and fully supervised scenarios, with ablation studies and visualization further support the use of our model for audio spatialization.

Self-Supervised Prototype Representation Learning for Event-Based Corporate Profiling

Event-based corporate profiling aims to assess the evolving operational status of the corresponding corporate from its event sequence. Existing studies on corporate profiling have partially addressed the problem via (i) case-by-case empirical analysis by leveraging traditional financial methods, or (ii) the automatic profile inference by reformulating the problem into a supervised learning task. However, both approaches heavily rely on domain knowledge and are labor-intensive. More importantly, the task-specific nature of both approaches prevents the obtained corporate profiles from being applied to diversified downstream applications. To this end, in this paper, we propose a Self-Supervised Prototype Representation Learning (SePaL) framework for dynamic corporate profiling. By exploiting the topological information of an event graph and exploring self-supervised learning techniques, SePaL can obtain unified corporate representations that are robust to event noises and can be easily fine-tuned to benefit various down-stream applications with only a few annotated data. Specifically, we first infer the initial cluster distribution of noise-resistant event prototypes based on latent representations of events. Then, we construct four permutation-invariant self-supervision signals to guide the representation learning of the event prototype. In terms of applications, we exploit the learned time-evolving corporate representations for both stock price spike prediction and corporate default risk evaluation. Experimental results on two real-world corporate event datasets demonstrate the effectiveness of SePaL for these two applications.

Contrastive Self-Supervised Learning With Smoothed Representation for Remote Sensing

In remote sensing, numerous unlabeled images are continuously accumulated over time, and it is difficult to annotate all the data. Therefore, a self-supervised learning technique that can improve the recognition rate using unlabeled data will be useful for remote sensing. This letter presents contrastive self-supervised learning with smoothed representation for remote sensing based on the SimCLR framework. In self-supervised learning for remote sensing, the well-known characteristic that images within a short distance might be semantically similar is usually used. Our algorithm is based on this knowledge, and it simultaneously utilizes several neighboring images as a positive pair of the anchor image, unlike existing methods such as Tile2Vec. Furthermore, MoCo and SimCLR, which are among the state-of-the-art self-supervised learning approaches, only use two augmented views of the single-input image, but our proposed approach uses multiple-input images and averages their representations (e.g., smoothed representation). Consequently, the proposed approach outperforms state-of-the-art self-supervised learning methods, such as Tile2Vec, MoCo, and SimCLR, in the cropland data layer (CDL), RESISC-45, UCMerced, and EuroSAT data sets. The proposed approach is comparable to the pretrained ImageNet model in the CDL classification task.

Audio-Visual Self-Supervised Terrain Type Recognition for Ground Mobile Platforms

The ability to recognize and identify terrain characteristics is an essential function required for many autonomous ground robots such as social robots, assistive robots, autonomous vehicles, and ground exploration robots. Recognizing and identifying terrain characteristics is challenging because similar terrains may have very different appearances (e.g., carpet comes in many colors), while terrains with very similar appearance may have very different physical properties (e.g., mulch versus dirt). In order to address the inherent ambiguity in vision-based terrain recognition and identification, we propose a multi-modal self-supervised learning technique that switches between audio features extracted from a microphone attached to the underside of a mobile platform and image features extracted by a camera on the platform to cluster terrain types. The terrain cluster labels are then used to train an image-based real-time CNN (Convolutional Neural Network) to predict terrain types changes. Through experiments, we demonstrate that the proposed self-supervised terrain type recognition method achieves over 80% accuracy, which greatly outperforms several baselines and suggests strong potential for assistive applications.

Self-Supervised Learning to Increase the Performance of Skin Lesion Classification

To successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study, we improve deep neural models training and increase the classification accuracy under a scarcity of data by the use of the self-supervised learning technique. Self-supervised learning allows an unlabeled dataset to be used for pretraining the network, as opposed to transfer learning that requires labeled datasets. The pretrained network can be then fine-tuned using the annotated data. Moreover, we investigated the effect of combining the self-supervised learning approach with transfer learning. It is shown that this strategy outperforms network training from scratch or with transfer learning. The tests were conducted on a very important and sensitive application (skin lesion classification), but the presented approach can be applied to a broader family of applications, especially in the medical domain where the scarcity of data is a real problem.

The Language of Innovation.

Predicting innovation is a peculiar problem in data science. Following its definition, an innovation is always a never-seen-before event, leaving no room for traditional supervised learning approaches. Here we propose a strategy to address the problem in the context of innovative patents, by defining innovations as never-seen-before associations of technologies and exploiting self-supervised learning techniques. We think of technological codes present in patents as a vocabulary and the whole technological corpus as written in a specific, evolving language. We leverage such structure with techniques borrowed from Natural Language Processing by embedding technologies in a high dimensional euclidean space where relative positions are representative of learned semantics. Proximity in this space is an effective predictor of specific innovation events, that outperforms a wide range of standard link-prediction metrics. The success of patented innovations follows a complex dynamics characterized by different patterns which we analyze in details with specific examples. The methods proposed in this paper provide a completely new way of understanding and forecasting innovation, by tackling it from a revealing perspective and opening interesting scenarios for a number of applications and further analytic approaches.

SPICE: Self-Supervised Pitch Estimation

We propose a model to estimate the fundamental frequency in monophonic audio, often referred to as pitch estimation. We acknowledge the fact that obtaining ground truth annotations at the required temporal and frequency resolution is a particularly daunting task. Therefore, we propose to adopt a self-supervised learning technique, which is able to estimate pitch without any form of supervision. The key observation is that pitch shift maps to a simple translation when the audio signal is analysed through the lens of the constant-Q transform (CQT). We design a self-supervised task by feeding two shifted slices of the CQT to the same convolutional encoder, and require that the difference in the outputs is proportional to the corresponding difference in pitch. In addition, we introduce a small model head on top of the encoder, which is able to determine the confidence of the pitch estimate, so as to distinguish between voiced and unvoiced audio. Our results show that the proposed method is able to estimate pitch at a level of accuracy comparable to fully supervised models, both on clean and noisy audio samples, although it does not require access to large labeled datasets.

Querying concepts in product data by means of query expansion

The Web has become the primary source of information containing both structured and unstructured information. A good example is e-commerce where products are usually described by technical specifications structured data and textual user reviews unstructured data. Both sources of information complement each other, covering quantifiable as well as perceived aspects of each product. In fact, for most searches users will have more or less abstract concepts in mind, as opposed to clear cut categorical information. In this paper, we develop a novel approach to reveal implicit product features for querying, by combining structured product data with natural-language product reviews. Using a self-supervised learning technique we progressively build a query-aware representation of the product domain under consideration. This representation can then effectively be used for intuitive querying. We performed extensive experiments confirming the effectiveness of our approach over real world product data. In particular, our evaluations show vastly improved precision and recall over the respective IR techniques.