相关论文: Transfer Value Iteration Networks

Deep models must learn robust and transferable representations in order to perform well on new domains. While domain transfer methods (e.g., domain adaptation, domain generalization) have been proposed to learn transferable representations…

Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…

The use of transfer learning with deep neural networks has increasingly become widespread for deploying well-tested computer vision systems to newer domains, especially those with limited datasets. We describe a transfer learning use case…

Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from multiple source domains and generalize to a target domain…

In real-world applications, it is often expensive and time-consuming to obtain labeled examples. In such cases, knowledge transfer from related domains, where labels are abundant, could greatly reduce the need for extensive labeling…

Transfer learning is an umbrella term for machine learning approaches that leverage knowledge gained from solving one problem (the source domain) to improve speed, efficiency, and data requirements in solving a different but related problem…

Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source domains (available at train time) to an, a priori, unseen target domain(s). This requires a class to be expressed in multiple domains for the…

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different…

Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain…

Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set. To alleviate the effect of `domain shift', the major challenge in domain adaptation,…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Data-driven methods -- such as machine learning and time series forecasting -- are widely used for sales forecasting in the food retail domain. However, for newly introduced products insufficient training data is available to train accurate…

Transferability estimation identifies the best pre-trained models for downstream tasks without incurring the high computational cost of full fine-tuning. This capability facilitates deployment and advances the pre-training and fine-tuning…

Social-aware recommendation approaches have been recognized as an effective way to solve the data sparsity issue of traditional recommender systems. The assumption behind is that the knowledge in social user-user connections can be shared…

Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them…

Unsupervised Domain Adaptation (UDA) methods facilitate knowledge transfer from a labeled source domain to an unlabeled target domain, navigating the obstacle of domain shift. While Convolutional Neural Networks (CNNs) are a staple in UDA,…

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model…

Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…