The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained. Unfortunately, such a problem setting is often impractical if not infeasible since many real-world tasks rely on sequential learning, e.g., data are decentralized or collected in a streaming fashion. In this paper, we conduct the first thorough and dedicated investigation on self-supervised pre-training with streaming data, aiming to shed light on the model behavior under this overlooked setup. Specifically, we pre-train over 500 models on four categories of pre-training streaming data from ImageNet and DomainNet and evaluate them on three types of downstream tasks and 12 different downstream datasets. Our studies show that, somehow beyond our expectation, with simple data replay or parameter regularization, sequential self-supervised pre-training turns out to be an efficient alternative for joint pre-training, as the performances of the former are mostly on par with those of the latter. Moreover, catastrophic forgetting, a common issue in sequential supervised learning, is much alleviated in sequential self-supervised learning (SSL), which is well justified through our comprehensive empirical analysis on representations and the sharpness of minima in the loss landscape. Our findings, therefore, suggest that, in practice, for SSL, the cumbersome joint training can be replaced mainly by sequential learning, which in turn enables a much broader spectrum of potential application scenarios.

In this paper, we examine self-supervised learning methods, particularly VICReg, to provide an information-theoretical understanding of their construction. As a first step, we demonstrate how information-theoretic quantities can be obtained for a deterministic network, offering a possible alternative to prior work that relies on stochastic models. This enables us to demonstrate how VICReg can be (re)discovered from first principles and its assumptions about data distribution. Furthermore, we empirically demonstrate the validity of our assumptions, confirming our novel understanding of VICReg. Finally, we believe that the derivation and insights we obtain can be generalized to many other SSL methods, opening new avenues for theoretical and practical understanding of SSL and transfer learning.

Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs, ls learns to split this dataset so that predictors trained on the training split cannot generalize to the testing split. This performance gap suggests that the testing split is under-represented in the dataset, which is a signal of potential bias. Identifying non-generalizable splits is challenging since we have no annotations about the bias. In this work, we show that the prediction correctness of each example in the testing split can be used as a source of weak supervision: generalization performance will drop if we move examples that are predicted correctly away from the testing split, leaving only those that are mis-predicted. ls is task-agnostic and can be applied to any supervised learning problem, ranging from natural language understanding and image classification to molecular property prediction. Empirical results show that ls is able to generate astonishingly challenging splits that correlate with human-identified biases. Moreover, we demonstrate that combining robust learning algorithms (such as group DRO) with splits identified by ls enables automatic de-biasing. Compared to previous state-of-the-art, we substantially improve the worst-group performance (23.4% on average) when the source of biases is unknown during training and validation.

We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance. To address the problems incurred by noisy pseudo boxes, we design Noisy Pseudo box Learning (NPL) that includes Prediction-guided Label Assignment (PLA) and Positive-proposal Consistency Voting (PCV). PLA relies on model predictions to assign labels and makes it robust to even coarse pseudo boxes; while PCV leverages the regression consistency of positive proposals to reflect the localization quality of pseudo boxes. Furthermore, in consistency training, we propose Multi-view Scale-invariant Learning (MSL) that includes mechanisms of both label-and feature-level consistency, where feature consistency is achieved by aligning shifted feature pyramids between two images with identical content but varied scales. On COCO benchmark, our method, termed PSEudo labeling and COnsistency training (PseCo), outperforms the SOTA (Soft Teacher) by 2.0, 1.8, 2.0 points under 1%, 5%, and 10% labelling ratios, respectively. It also significantly improves the learning efficiency for SSOD, e.g., PseCo halves the training time of the SOTA approach but achieves even better performance. Code is available at https://github.com/ligang-cs/PseCo. Keywords: Semi-supervised Learning, Object Detection

The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

Semi-supervised learning (SSL) is a common approach to learning predictive models using not only labeled examples, but also unlabeled examples. While SSL for the simple tasks of classification and regression has received a lot of attention from the research community, this is not properly investigated for complex prediction tasks with structurally dependent variables. This is the case of multi-label classification and hierarchical multi-label classification tasks, which may require additional information, possibly coming from the underlying distribution in the descriptive space provided by unlabeled examples, to better face the challenging task of predicting simultaneously multiple class labels. In this paper, we investigate this aspect and propose a (hierarchical) multi-label classification method based on semi-supervised learning of predictive clustering trees. We also extend the method towards ensemble learning and propose a method based on the random forest approach. Extensive experimental evaluation conducted on 23 datasets shows significant advantages of the proposed method and its extension with respect to their supervised counterparts. Moreover, the method preserves interpretability and reduces the time complexity of classical tree-based models.

Federated Learning is a new machine learning paradigm dealing with distributed model learning on independent devices. One of the many advantages of federated learning is that training data stay on devices (such as smartphones), and only learned models are shared with a centralized server. In the case of supervised learning, labeling is entrusted to the clients. However, acquiring such labels can be prohibitively expensive and error-prone for many tasks, such as human activity recognition. Hence, a wealth of data remains unlabelled and unexploited. Most existing federated learning approaches that focus mainly on supervised learning have mostly ignored this mass of unlabelled data. Furthermore, it is unclear whether standard federated Learning approaches are suited to self-supervised learning. The few studies that have dealt with the problem have limited themselves to the favorable situation of homogeneous datasets. This work lays the groundwork for a reference evaluation of federated Learning with Semi-Supervised Learning in a realistic setting. We show that standard lightweight autoencoder and standard Federated Averaging fail to learn a robust representation for Human Activity Recognition with several realistic heterogeneous datasets. These findings advocate for a more intensive research effort in Federated Self Supervised Learning to exploit the mass of heterogeneous unlabelled data present on mobile devices.

In the past few weeks, I've been doing research on Linear Regression in Data Science. This week, however, I wanted to change things up. We know a little bit about supervised learning methods and unsupervised learning methods, but we haven't spoken about a different type of learning: Reinforcement Learning. This is the type of learning that would require no supervision, like unsupervised learning, but has unique qualities as well. Before we dive in, one quick note is that Reinforcement Learning is not as widely used as other models, such as Supervised Learning Methods.

Self-Supervised Learning (SSL) has become a very active area of Deep Learning research where it is heavily used as a pre-training method for classification and other tasks. However, the rapid pace of advancements in this area comes at a price: training pipelines vary significantly across papers, which presents a potentially crucial confounding factor. Here, we show that, indeed, the choice of hyperparameters and data augmentation strategies can have a dramatic impact on performance. To shed light on these neglected factors and help maximize the power of SSL, we hyperparameterize these components and optimize them with Bayesian optimization, showing improvements across multiple datasets for the SimSiam SSL approach. Realizing the importance of data augmentations for SSL, we also introduce a new automated data augmentation algorithm, GroupAugment, which considers groups of augmentations and optimizes the sampling across groups. In contrast to algorithms designed for supervised learning, GroupAugment achieved consistently high linear evaluation accuracy across all datasets we considered. Overall, our results indicate the importance and likely underestimated role of data augmentation for SSL.