Related papers: Gradient Regularized Contrastive Learning for Cont…
Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…
Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in…
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional…
Unsupervised domain adaptation (UDA) intends to transfer knowledge from a labeled source domain to an unlabeled target domain. Many current methods focus on learning feature representations that are both discriminative for classification…
Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, such methods typically…
Unsupervised domain adaptation (UDA) for semantic segmentation has been well-studied in recent years. However, most existing works largely neglect the local regional consistency across different domains and are less robust to changes in…
Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains.…
Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message…
Graph contrastive learning (GCL) has emerged as a pivotal technique in the domain of graph representation learning. A crucial aspect of effective GCL is the caliber of generated positive and negative samples, which is intrinsically dictated…
Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…
Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains. However, the most common InfoNCE-based methods suffer from some dilemmas, such as \textit{uniformity-tolerance dilemma} (UTD) and…
Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…
Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not…
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA.…
Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the…
We consider the problem of unsupervised domain adaptation in semantic segmentation. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy…
The ability of neural networks to continuously learn and adapt to new tasks while retaining prior knowledge is crucial for many applications. However, current neural networks tend to forget previously learned tasks when trained on new ones,…
Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform.…
Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…