Related papers: Pretraining Respiratory Sound Representations usin…
Deep learning-based recommender systems have achieved remarkable success in recent years. However, these methods usually heavily rely on labeled data (i.e., user-item interactions), suffering from problems such as data sparsity and…
Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…
With the onset of the COVID-19 pandemic, ultrasound has emerged as an effective tool for bedside monitoring of patients. Due to this, a large amount of lung ultrasound scans have been made available which can be used for AI based diagnosis…
Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply…
Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…
Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…
Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…
Citation classification, which identifies the intention behind academic citations, is pivotal for scholarly analysis. Previous works suggest fine-tuning pretrained language models (PLMs) on citation classification datasets, reaping the…
We explore the value of weak labels in learning transferable representations for medical images. Compared to hand-labeled datasets, weak or inexact labels can be acquired in large quantities at significantly lower cost and can provide…
Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…
Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…
Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in the latent space.…
Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…
Advances in self-supervised learning (SSL) have shown that self-supervised pretraining on medical imaging data can provide a strong initialization for downstream supervised classification and segmentation. Given the difficulty of obtaining…
Deep learning has been widely used recently for sound event detection and classification. Its success is linked to the availability of sufficiently large datasets, possibly with corresponding annotations when supervised learning is…
Contrastive learning has been proved to be a promising technique for image-level representation learning from unlabeled data. Many existing works have demonstrated improved results by applying contrastive learning in classification and…
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-shot learning…
We introduce COLA, a self-supervised pre-training approach for learning a general-purpose representation of audio. Our approach is based on contrastive learning: it learns a representation which assigns high similarity to audio segments…
Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquisition parameters, such as echo time and repetition time,…