Related papers: Unified Multi-Domain Learning and Data Imputation …

Unsupervised model transfer has the potential to greatly improve the generalizability of deep models to novel domains. Yet the current literature assumes that the separation of target data into distinct domains is known as a priori. In this…

Self-training emerges as an important research line on domain adaptation. By taking the model's prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances in the target domain. However,…

Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy made a significant breakthrough in the adaptability of…

Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the…

Predictive models trained on imbalanced data tend to produce biased results. This problem is exacerbated when there is not just one output label, but a set of them. This is the case for multilabel learning (MLL) algorithms used to classify…

Multitask learning (MTL) has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, to solve them simultaneously while minimizing data sharing…

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…

Both limited annotation and domain shift are significant challenges frequently encountered in medical image segmentation, leading to derivative scenarios like semi-supervised medical (SSMIS), semi-supervised medical domain generalization…

Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…

In multi-stage processes, decisions occur in an ordered sequence of stages. Early stages usually have more observations with general information (easier/cheaper to collect), while later stages have fewer observations but more specific data.…

Label Distribution Learning (LDL) is a novel machine learning paradigm that assigns label distribution to each instance. Many LDL methods proposed to leverage label correlation in the learning process to solve the exponential-sized output…

Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-making and postoperative analysis in robotic surgery. However,…

Accurately discriminating progressive stages of Alzheimer's Disease (AD) is crucial for early diagnosis and prevention. It often involves multiple imaging modalities to understand the complex pathology of AD, however, acquiring a complete…

In this work, we propose a simple yet effective method to tackle the problem of imbalanced multi-class semantic segmentation in deep learning systems. One of the key properties for a good training set is the balancing among the classes.…

Multi-task learning (MTL) in materials science relies on the assumption that physically related properties share learnable representations. We challenge this assumption using a 54,028-sample metal alloy dataset exhibiting extreme task-level…

Semi-Supervised Learning (SSL) is implemented when algorithms are trained on both labeled and unlabeled data. This is a very common application of ML as it is unrealistic to obtain a fully labeled dataset. Researchers have tackled three…

Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on limited datasets, or…

Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…