Related papers: Looking back at Labels: A Class based Domain Adapt…

Object recognition from images means to automatically find object(s) of interest and to return their category and location information. Benefiting from research on deep learning, like convolutional neural networks~(CNNs) and generative…

Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source domains may be very expensive, making complete labeling as…

Numerous algorithms have been proposed for transferring knowledge from a label-rich domain (source) to a label-scarce domain (target). Almost all of them are proposed for a closed-set scenario, where the source and the target domain…

Human parsing has been extensively studied recently due to its wide applications in many important scenarios. Mainstream fashion parsing models focus on parsing the high-resolution and clean images. However, directly applying the parsers…

We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance…

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…

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…

Most studies on learning from noisy labels rely on unrealistic models of i.i.d. label noise, such as class-conditional transition matrices. More recent work on instance-dependent noise models are more realistic, but assume a single…

The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can…

Domain adversarial adaptation in a continual setting poses a significant challenge due to the limitations on accessing previous source domain data. Despite extensive research in continual learning, the task of adversarial adaptation cannot…

Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any…

Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing methods aim to minimize this domain-shift using auxiliary…

Domain adaptation manages to transfer the knowledge of well-labeled source data to unlabeled target data. Many recent efforts focus on improving the prediction accuracy of target pseudo-labels to reduce conditional distribution shift. In…

Domain adaptation is transfer learning which aims to generalize a learning model across training and testing data with different distributions. Most previous research tackle this problem in seeking a shared feature representation between…

Domain adaptation aims to mitigate distribution shifts among different domains. However, traditional formulations are mostly limited to categorical domains, greatly simplifying nuanced domain relationships in the real world. In this work,…

Semantic segmentation is an important sub-task for many applications, but pixel-level ground truth labeling is costly and there is a tendency to overfit the training data, limiting generalization. Unsupervised domain adaptation can…

Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g.…

Adversarial learning has demonstrated good performance in the unsupervised domain adaptation setting, by learning domain-invariant representations. However, recent work has shown limitations of this approach when label distributions differ…

In the problem of domain adaptation for binary classification, the learner is presented with labeled examples from a source domain, and must correctly classify unlabeled examples from a target domain, which may differ from the source.…

Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…