AutoDIAL: Automatic Domain Alignment Layers

Cariucci, Fabio M.; Porzi, Lorenzo; Caputo, Barbara; Ricci, Elisa; Bulò, Samuel Rota

doi:10.1109/iccv.2017.542

Cited by 257 publications

(287 citation statements)

References 7 publications

Supporting

Mentioning

284

Contrasting

Unclassified

Order By: Relevance

“…Traditional methods for domain adaptation involve minimizing some measure of distance between the source and * This work was done when Yunsheng Li is an intern at Microsoft Cloud & AI the target distributions. Two commonly used measures are the first and second order moment [2], and learning the distance metrics using Adversarial approaches [34,35]. Both approaches have had good success in the classification problems (e.g., MNIST [16], USPS [7] and SVHN [22]); however, as pointed out in [37], their performance is quite limited on the semantic segmentation problem.…”

Section: Introductionmentioning

confidence: 99%

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Liu

Vasconcelos

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

598

583

View full text Add to dashboard Cite

Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on limited datasets, or yield not so good performance compared with supervised learning. In this paper, we propose a novel bidirectional learning framework for domain adaptation of segmentation. Using the bidirectional learning, the image translation model and the segmentation adaptation model can be learned alternatively and promote to each other. Furthermore, we propose a self-supervised learning algorithm to learn a better segmentation adaptation model and in return improve the image translation model. Experiments show that our method is superior to the state-of-the-art methods in domain adaptation of segmentation with a big margin. The source code is available at https://github.com/liyunsheng13/BDL.On the forward direction (i.e., "translation-tosegmentation", similar to [12,36]), we propose a self-supervised learning (SSL) approach in training our segmentation adaptation model. Different from segmentation models trained on real data, the segmentation adaptation model is trained on both synthetic and real datasets, but the real data has no annotations. At every time, we may regard the predicted labels for real data with high confidence as the approximation to the ground truth

show abstract

Section: Introductionmentioning

confidence: 99%

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Liu

Vasconcelos

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

598

583

View full text Add to dashboard Cite

show abstract

“…AlexNet [41] (DDC) [9], domain-adversarial training of neural networks (DANN) [15], deep-CORAL (D-CORAL) [13], deep adaptation networks (DAN) [10], deep reconstruction classification network (DRCN) [44], residual transfer network (RTN) [11], joint adaptation network (JAN) [12], domain adaptive hashing (DAH) [26], adversarial discriminative aomain adaptation (ADDA) [16], automatic domain alignment layers (AutoDIAL) [17], and multi-adversarial domain adaptation (MADA) [45]. For the PACS dataset, Office-31 and…”

Section: Baseline Methodsmentioning

confidence: 99%

Correlation-aware adversarial domain adaptation and generalization

Rahman

Fookes

Baktashmotlagh

et al. 2020

Pattern Recognition

109

View full text Add to dashboard Cite

Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different. The task of DG is more challenging than DA as the target data is totally unseen during the training phase in DG scenarios. The current state-of-the-art employs adversarial techniques, however, these are rarely considered for the DG problem. Furthermore, these approaches do not consider correlation alignment which has been proven highly beneficial for minimizing domain discrepancy. In this paper, we propose a correlation-aware adversarial DA and DG framework where the features of the source and target data are minimized using correlation alignment along with adversarial learning.Incorporating the correlation alignment module along with adversarial learning helps to achieve a more domain agnostic model due to the improved ability to reduce domain discrepancy with unlabeled target data more effectively. Experiments on benchmark datasets serve as evidence that our proposed method yields improved state-of-the-art performance.

show abstract

“…[9] proposed to align the source and target distributions by minimizing the Maximum Mean Discrepancy (MMD). Driven by a similar motivation, Adaptive Batch Normalization (AdaBN) [20] and AutoDial [22] align the distributions via modified batch normalization layers. Domain Adversarial Neural Networks (DANN) [8] aim at aligning the distributions by using a domain discriminator and train the model adversarially in order to make the feature space indistinguishable for the different domains.…”

Section: A Domain Adaptationmentioning

confidence: 99%

Missing-Class-Robust Domain Adaptation by Unilateral Alignment

Wang

Michau

Fink

2021

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

Domain adaptation aims at improving model performance by leveraging the learned knowledge in the source domain and transferring it to the target domain. Recently, domain adversarial methods have been particularly successful in alleviating the distribution shift between the source and the target domains. However, these methods assume an identical label space between the two domains. This assumption imposes a significant limitation for real applications since the target training set may not contain the complete set of classes. We demonstrate in this paper that the performance of domain adversarial methods can be vulnerable to an incomplete target label space during training. To overcome this issue, we propose a two-stage unilateral alignment approach. The proposed methodology makes use of the inter-class relationships of the source domain and aligns unilaterally the target to the source domain. The benefits of the proposed methodology are first evaluated on the MNIST→MNIST-M adaptation task. The proposed methodology is also evaluated on a fault diagnosis task, where the problem of missing fault types in the target training dataset is common in practice. Both experiments demonstrate the effectiveness of the proposed methodology.Index Terms-fault diagnosis, domain adaptation, feature alignment

show abstract

AutoDIAL: Automatic Domain Alignment Layers

Cited by 257 publications

References 7 publications

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Correlation-aware adversarial domain adaptation and generalization

Missing-Class-Robust Domain Adaptation by Unilateral Alignment

Contact Info

Product

Resources

About