Related papers: DoCoGen: Domain Counterfactual Generation for Low …
Although current face anti-spoofing methods achieve promising results under intra-dataset testing, they suffer from poor generalization to unseen attacks. Most existing works adopt domain adaptation (DA) or domain generalization (DG)…
Cross-lingual Named Entity Recognition (NER) has recently become a research hotspot because it can alleviate the data-hungry problem for low-resource languages. However, few researches have focused on the scenario where the source-language…
Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks. In order for such models to truly be useful, they must be capable of correctly generating utterances for…
Counterfactual Data Augmentation (CDA) has been one of the preferred techniques for mitigating gender bias in natural language models. CDA techniques have mostly employed word substitution based on dictionaries. Although such…
An effective method of teaching across disciplines is to provide examples of high-quality work. However, an example may be significantly different from a student's current work, making it challenging for them to emulate. An ideal learning…
In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as…
While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data distributions. In this work, we introduce…
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to…
Neural networks are known to be data hungry and domain sensitive, but it is nearly impossible to obtain large quantities of labeled data for every domain we are interested in. This necessitates the use of domain adaptation strategies. One…
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing…
Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First,…
Current unsupervised domain adaptation (UDA) methods for semantic segmentation typically assume identical class labels between the source and target domains. This assumption ignores the label-level domain gap, which is common in real-world…
As one of the most exciting features of large language models (LLMs), in-context learning is a mixed blessing. While it allows users to fast-prototype a task solver with only a few training examples, the performance is generally sensitive…
Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional…
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…
The problem of Domain Adaptive in the field of Object Detection involves the transfer of object detection models from labeled source domains to unannotated target domains. Recent advancements in this field aim to address domain…
Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…
Powerful generative adversarial networks (GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we…
The generalization power of deep-learning models is dependent on rich-labelled data. This supervision using large-scaled annotated information is restrictive in most real-world scenarios where data collection and their annotation involve…
Recent advances in domain adaptation establish that requiring a low risk on the source domain and equal feature marginals degrade the adaptation's performance. At the same time, empirical evidence shows that incorporating an unsupervised…