Related papers: SelfReplay: Adapting Self-Supervised Sensory Model…

Domain adaptation becomes more challenging with increasing gaps between source and target domains. Motivated from an empirical analysis on the reliability of labeled source data for the use of distancing target domains, we propose…

Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly. Recently published research has shown that adapting the…

Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…

Few-shot meta-learning methods consider the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks. However, in many real world settings, it is more natural to…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…

Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…

Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple…

We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new…

Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the…

Question answering has seen significant advances in recent times, especially with the introduction of increasingly bigger transformer-based models pre-trained on massive amounts of data. While achieving impressive results on many…

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to…

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…

Most research on domain adaptation has focused on the purely unsupervised setting, where no labeled examples in the target domain are available. However, in many real-world scenarios, a small amount of labeled target data is available and…

We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts. We conduct a wide range of…

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on…

In the domain of single-view 3D reconstruction, traditional techniques have frequently relied on expensive and time-intensive 3D annotation data. Facing the challenge of annotation acquisition, semi-supervised learning strategies offer an…

Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch…