Related papers: Neural Structural Correspondence Learning for Doma…
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised Learning (SSL) methods are promising to reduce the…
Self-Supervised Learning (SSL) is an important paradigm for learning representations from unlabelled data, and SSL with neural networks has been highly successful in practice. However current theoretical analysis of SSL is mostly restricted…
Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domain, making most…
Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and…
Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do not capture pixel-level domain shifts that are crucial for…
In recent years, Spiking Neural Networks (SNNs) have demonstrated great successes in completing various Machine Learning tasks. We introduce a method for learning image features by \textit{locally connected layers} in SNNs using…
The goal of this paper is to use multi-task learning to efficiently scale slot filling models for natural language understanding to handle multiple target tasks or domains. The key to scalability is reducing the amount of training data…
Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels. We propose that advantages may be derived by…
Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a…
Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the…
Neural language models have achieved state-of-the-art performances on many NLP tasks, and recently have been shown to learn a number of hierarchically-sensitive syntactic dependencies between individual words. However, equally important for…
Domain adaptation of visual detectors is a critical challenge, yet existing methods have overlooked pixel appearance transformations, focusing instead on bootstrapping and/or domain confusion losses. We propose a Semantic Pixel-Level…
Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate…
We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a…
Semantic segmentation's performance is often compromised when applied to unlabeled adverse weather conditions. Unsupervised domain adaptation is a potential approach to enhancing the model's adaptability and robustness to adverse weather.…
Learning algorithms for natural language processing (NLP) tasks traditionally rely on manually defined relevant contextual features. On the other hand, neural network models using an only distributional representation of words have been…
Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation,…
Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain generalization methods learn domain invariant features by…
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…
The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and…