Related papers: Transfer and Alignment Network for Generalized Cat…
This paper addresses challenges in robust transfer learning stemming from ambiguity in Bayes classifiers and weak transferable signals between the target and source distribution. We introduce a novel quantity called the ''ambiguity level''…
Generative adversarial networks (GANs) have shown impressive results in both unconditional and conditional image generation. In recent literature, it is shown that pre-trained GANs, on a different dataset, can be transferred to improve the…
We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classification of healthy and cancer cells acquired by quantitative…
The existed methods for electroencephalograph (EEG) emotion recognition always train the models based on all the EEG samples indistinguishably. However, some of the source (training) samples may lead to a negative influence because they are…
Transfer Learning is an area of statistics and machine learning research that seeks answers to the following question: how do we build successful learning algorithms when the data available for training our model is qualitatively different…
Fine-grained classification remains a very challenging problem, because of the absence of well-labeled training data caused by the high cost of annotating a large number of fine-grained categories. In the extreme case, given a set of test…
Anomaly detection (AD) plays a pivotal role in numerous web-based applications, including malware detection, anti-money laundering, device failure detection, and network fault analysis. Most methods, which rely on unsupervised learning, are…
GANs largely increases the potential impact of generative models. Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a…
Domain adaptation aims to mitigate the domain shift problem when transferring knowledge from one domain into another similar but different domain. However, most existing works rely on extracting marginal features without considering class…
Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…
In this paper, we consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled…
Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest. Numerous tricks and techniques have been proposed to ensure robust learning on arbitrary streams of unlabeled data.…
A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to…
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task…
In this paper, a new approach for classification of target task using limited labeled target data as well as enormous unlabeled source data is proposed which is called self-taught learning. The target and source data can be drawn from…
In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…
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…
Open set domain recognition has got the attention in recent years. The task aims to specifically classify each sample in the practical unlabeled target domain, which consists of all known classes in the manually labeled source domain and…
Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Existing class-wise targeted attacks remain impractical for stealthy exploitation in this…