Related papers: Cross-domain Open-world Discovery
Unsupervised domain adaptation aims to train a classification model from the labeled source domain for the unlabeled target domain. Since the data distributions of the two domains are different, the model often performs poorly on the target…
Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples…
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on…
Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for multimedia applications. Existing…
Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of…
Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. In practice, little may be known about the category overlap between the two domains. While some methods address target…
Generalized category discovery (GCD) is a pragmatic but underexplored problem, which requires models to automatically cluster and discover novel categories by leveraging the labeled samples from old classes. The challenge is that unlabeled…
Open-world machine learning is an emerging technique in artificial intelligence, where conventional machine learning models often follow closed-world assumptions, which can hinder their ability to retain previously learned knowledge for…
Applying the knowledge of an object detector trained on a specific domain directly onto a new domain is risky, as the gap between two domains can severely degrade model's performance. Furthermore, since different instances commonly embody…
This paper addresses cross-domain visual search, where visual queries retrieve category samples from a different domain. For example, we may want to sketch an airplane and retrieve photographs of airplanes. Despite considerable progress,…
Unsupervised novelty detection (UND), aimed at identifying novel samples, is essential in fields like medical diagnosis, cybersecurity, and industrial quality control. Most existing UND methods assume that the training data and testing…
With the development of generative artificial intelligence, new forgery methods are rapidly emerging. Social platforms are flooded with vast amounts of unlabeled synthetic data and authentic data, making it increasingly challenging to…
Previous contrastive deep clustering methods mostly focus on instance-level information while overlooking the member relationship within groups/clusters, which may significantly undermine their representation learning and clustering…
Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain invariant optimal…
Moving deep learning models from the laboratory setting to the open world entails preparing them to handle unforeseen conditions. In several applications the occurrence of novel classes during deployment poses a significant threat, thus it…
Albeit the notable performance on in-domain test points, it is non-trivial for deep neural networks to attain satisfactory accuracy when deploying in the open world, where novel domains and object classes often occur. In this paper, we…
We address the problem of generalized category discovery (GCD) in this paper, i.e. clustering the unlabeled images leveraging the information from a set of seen classes, where the unlabeled images could contain both seen classes and unseen…
In real-world graph data, distribution shifts can manifest in various ways, such as the emergence of new categories and changes in the relative proportions of existing categories. It is often important to detect nodes of novel categories…
Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and…
It is essential for safety-critical applications of deep neural networks to determine when new inputs are significantly different from the training distribution. In this paper, we explore this out-of-distribution (OOD) detection problem for…