(2) 我们设计了一个名为MADAN的新框架来进行语义分割的MDA。除了特征级对齐之外,还通过为每个源循环生成一个自适应域来进一步考虑像素级对齐,该域与新的动态语义一致性损失保持一致。提出了子域聚合鉴别器和跨域循环鉴别器,以更好地对齐不同的自适应域。(3) 我们从合成的GTA和SYNTHIA到真实的Cityscapes和BDDS数据...
However, under joint training of multi-source domains, some difficulties such as domain imbalance, domain shifts and small training batches not only influence the representation learning of the model but also lead to poor generalization performance. In this work, we enhance the generalization ...
Domain adaptationMulti-source learningMaximum mean discrepancySample reweightingIn recent years, domain adaptation and transfer learning are known as promising techniques with admirable performance to deal with problems with distribution difference between the training (source domain) and test (target domain)...
Recent works of multi-source domain adaptation focus on learning a domain-agnostic model, of which the parameters are static. However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a performance degradation in both source domains and target domain. ...
mains.Multi-sourcedomainadaptation(MDA) isapowerfulextensioninwhichthelabeleddata maybecollectedfrommultiplesourceswithdiffer- entdistributions.DuetothesuccessofDAmeth- odsandtheprevalenceofmulti-sourcedata,MDA hasattractedincreasingattentioninbothacademia andindustry.Inthissurvey,wedefinevarious MDAstrategiesandsumma...
Warehouse dwell time (WDT) of a truck is a critical metric for evaluating plant-logistics efficiency, including the time of the truck's queuing outside and loading inside the warehouse. But WDT prediction is challenging as it is affected by diverse factors like loading distinct types and ...
Multi-source domain adaptation involves multiple concurrent task learning, and the gradients are simultaneously back propagated. We validate the proposed framework on multi-source cross-domain sentiment classification datasets in Chinese and English. The experimental results demonstrate that the proposed ...
The most remarkable characteristic of transfer learning is that it can employ the knowledge in relative domains to help perform the learning tasks in the domain of the target. With the use of different fields of knowledge for target task learning, transfer learning can transfer and share the info...
Source free domain adaptationmulti-institutions data sharingprivacy protectionGreat progress has been made in diagnosing medical diseases based on deep learning. Large-scale medical data are expected to improve deep learning performance further. It is almost impossible for a single institution to collect ...
To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that the labeled data are sampled from a single source domain, which...