Related papers: MLAN: Multi-Level Adversarial Network for Domain A…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…

In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment. The variations of illumination, style, scale, and appearance in different domains can…

Multi-domain text classification (MDTC) aims to leverage all available resources from multiple domains to learn a predictive model that can generalize well on these domains. Recently, many MDTC methods adopt adversarial learning,…

Domain shift poses a significant challenge in Cross-Domain Facial Expression Recognition (CD-FER) due to the distribution variation across different domains. Current works mainly focus on learning domain-invariant features through global…

In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well…

Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to find efficient similarity metrics to compare the similarity…

With the rapid growth of multimedia data, such as image and text, it is a highly challenging problem to effectively correlate and retrieve the data of different media types. Naturally, when correlating an image with textual description,…

Machine learning (ML) provides effective means to learn from spectrum data and solve complex tasks involved in wireless communications. Supported by recent advances in computational resources and algorithmic designs, deep learning (DL) has…

Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to…

Partial domain adaptation aims to transfer knowledge from a label-rich source domain to a label-scarce target domain which relaxes the fully shared label space assumption across different domains. In this more general and practical…

The individual difference between subjects is significant in EEG-based emotion recognition, resulting in the difficulty of sharing the model across subjects. Previous studies use domain adaptation algorithms to minimize the global domain…

Unsupervised domain adaptation aims to learn a model of classifier for unlabeled samples on the target domain, given training data of labeled samples on the source domain. Impressive progress is made recently by learning invariant features…

Audio-visual speech recognition (AVSR) attracts a surge of research interest recently by leveraging multimodal signals to understand human speech. Mainstream approaches addressing this task have developed sophisticated architectures and…

Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive…

Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled data set from source domain and a target domain with a few labeled and many…

The varying cortical geometry of the brain creates numerous challenges for its analysis. Recent developments have enabled learning surface data directly across multiple brain surfaces via graph convolutions on cortical data. However,…

A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…