Related papers: Explaining, Analyzing, and Probing Representations…

Ice-containing clouds strongly impact climate, but they are hard to model due to ice crystal habit (i.e., shape) diversity. We use self-supervised learning (SSL) to learn latent representations of crystals from ice crystal imagery. By…

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of…

Discovering what is learned by neural networks remains a challenge. In self-supervised learning, classification is the most common task used to evaluate how good a representation is. However, relying only on such downstream task can limit…

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work,…

The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different…

Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases,…

With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream tasks. However, we find that current SSL models suffer severe…

Supervised Deep Learning (DL) models are currently the leading approach for sensor-based Human Activity Recognition (HAR) on wearable and mobile devices. However, training them requires large amounts of labeled data whose collection is…

Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn superior auditory representations. In this…

Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…

A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is an expensive task, unsupervised and semi-supervised learning…

Despite impressive empirical advances of SSL in solving various tasks, the problem of understanding and characterizing SSL representations learned from input data remains relatively under-explored. We provide a comparative analysis of how…

Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition. In this paper, we study which factor leads to the success of…

Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on…

The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…

Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…

Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent…

Mid-level vision capabilities - such as generic object localization and 3D geometric understanding - are not only fundamental to human vision but are also crucial for many real-world applications of computer vision. These abilities emerge…

Learning self-supervised image representations has been broadly studied to boost various visual understanding tasks. Existing methods typically learn a single level of image semantics like pairwise semantic similarity or image clustering…

Some of the threats in the dynamic environment include the unpredictability of the motion of objects and interferences to the robotic grasp. In such conditions the traditional supervised and reinforcement learning approaches are ill suited…