Related papers: Subject Invariant Contrastive Learning for Human A…

Contrastive learning has gained significant attention in skeleton-based action recognition for its ability to learn robust representations from unlabeled data. However, existing methods rely on a single skeleton convention, which limits…

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,…

Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates. While traditional systems interacting with students suffered from data sparsity and overfitting,…

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss…

The effectiveness of contrastive learning technology in natural language processing tasks is yet to be explored and analyzed. How to construct positive and negative samples correctly and reasonably is the core challenge of contrastive…

Through minimization of an appropriate loss function such as the InfoNCE loss, contrastive learning (CL) learns a useful representation function by pulling positive samples close to each other while pushing negative samples far apart in the…

We present a new adversarial deep learning framework for the problem of human activity recognition (HAR) using inertial sensors worn by people. Our framework incorporates a novel adversarial activity-based discrimination task that addresses…

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…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named Joint Contrastive Learning (JCL). JCL implicitly involves the…

Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation. However, training a neural network in a supervised manner requires a large amount of annotated labels which…

Sensor-based human activity recognition (HAR), i.e., the ability to discover human daily activity patterns from wearable or embedded sensors, is a key enabler for many real-world applications in smart homes, personal healthcare, and urban…

Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks. It is challenging to adopt vanilla contrastive learning technologies…

For object detection detectors, enhancing model performance hinges on the ability to simultaneously consider inconsistencies across tasks and focus on difficult-to-train samples. Achieving this necessitates incorporating information from…

Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have…

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…

Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article,…

Given a similarity metric, contrastive methods learn a representation in which examples that are similar are pushed together and examples that are dissimilar are pulled apart. Contrastive learning techniques have been utilized extensively…

Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge. To improve the model's generalization ability to the new domain…