Attending to Discriminative Certainty for Domain Adaptation

Kurmi, Vinod K; Kumar, Srijan; Namboodiri, Vinay P.

doi:10.1109/cvpr.2019.00058

Cited by 96 publications

(33 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, another method to solve this problem employs the multibranch general structure (Wang et al 2019). And CADA (Kurmi, Kumar, and Namboodiri 2019) proposes to find adaptable regions using some estimate of the discriminator. It pays most attention to detect whether the part of the picture is transferable or not and does not take the class-level semantic feature into count.…”

Section: Generative Domain Adaptationmentioning

confidence: 99%

Bi-Directional Generation for Unsupervised Domain Adaptation

Yang

Xia

Ding

et al. 2020

AAAI

View full text Add to dashboard Cite

Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. To balance the mitigation of domain gap and the preservation of the inherent structure, we propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains. Specifically, two cross-domain generators are employed to synthesize one domain conditioned on the other. The performance of our proposed method can be further enhanced by the consistent classifiers and the cross-domain alignment constraints. We also design two classifiers which are jointly optimized to maximize the consistency on target sample prediction. Extensive experiments verify that our proposed model outperforms the state-of-the-art on standard cross domain visual benchmarks.

show abstract

Section: Generative Domain Adaptationmentioning

confidence: 99%

Bi-Directional Generation for Unsupervised Domain Adaptation

Yang

Xia

Ding

et al. 2020

AAAI

View full text Add to dashboard Cite

show abstract

“…In addition, through using attention model idea, the transferable regions or images can be focused which are useful for domain adaptation [40][41].…”

Section: Related Workmentioning

confidence: 99%

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Jia

Sun

2020

IEEE Access

View full text Add to dashboard Cite

Although most transfer learning methods can reduce the difference of the feature distributions between the source and target domains effectively, some classes in the two domains may still be misaligned after domain adaptation, especially for the classes with similar features such as "bicycle" and "motorcycle". Therefore, a graph regularization based adversarial network model is proposed, whose innovations mainly include the following two aspects: First, a constraint function which is used to measure the difference between the features belonged to different classes is proposed, whose purpose is that not only the training accuracy is taken into account during supervised training, but also the difference between classes should be enlarged as much as possible; Then, a graph regularization constraint function is proposed, which makes all the classes have good local preserving properties after domain adaptation, and further reduces the possibility of all classes being misaligned. Experimental results on several cross-domain benchmark datasets show that our newly proposed approach outperforms state of the art methods.

show abstract

“…[41] suggested a method to measure predictive uncertainty with the help of model and data uncertainty. Recently, [42] proposed a certainty method to bring two data distributions close for the domain adaption task.…”

Section: Related Workmentioning

confidence: 99%

U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps

Patro

Lunayach

Patel

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question answering task. We incorporate modern probabilistic deep learning methods that we further improve by using the gradients for these estimates. These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions. The improved attention maps result in consistent improvement for various methods for visual question answering. Therefore, the proposed technique can be thought of as a recipe for obtaining improved certainty estimates and explanations for deep learning models. We provide detailed empirical analysis for the visual question answering task on all standard benchmarks and comparison with state of the art methods.

show abstract

Attending to Discriminative Certainty for Domain Adaptation

Cited by 96 publications

References 36 publications

Bi-Directional Generation for Unsupervised Domain Adaptation

Bi-Directional Generation for Unsupervised Domain Adaptation

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps

Contact Info

Product

Resources

About