Attending to Discriminative Certainty for Domain Adaptation

By Vinod Kumar Kurmi, Shanu Kumar, Vinay P. Namboodiri. 2019

113 citations recorded by the source corpus.

In this paper, we aim to solve for unsupervised domain adaptation of classifiers where we have access to label information for the source domain while these are not available for a target domain. While various methods have been proposed for solving these including adversarial discriminator based methods, most approaches have focused on the entire image based domain adaptation. In an image, there would be regions that can be adapted better, for instance, the foreground object may be similar in nature. To obtain such regions, we propose methods that consider the probabilistic certainty estimate of various regions and specific focus on these during classification for adaptation. We observe that just by incorporating the probabilistic certainty of the discriminator while training the classifier, we are able to obtain state of the art results on various datasets as compared against all the recent methods. We provide a thorough empirical analysis of the method by providing ablation analysis, statistical significance test, and visualization of the attention maps and t-SNE embeddings. These evaluations convincingly demonstrate the effectiveness of the proposed approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Do not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting (2021, methodology): “We obtain these uncertainties in a manner similar to [14, 20, 30, 19].”
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering (2020, background): “Some works [30, 56, 57] focus attention on transferable regions to derive a domain-invariant classification model.”
Unsupervised Domain Adaptation of Object Detectors: A Survey (2021, unknown): “…has been extensively studied for the task of classiﬁ-cation [27], [28], [24], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], and semantic segmentation [25], [44], [45], [46], [47], [48], [49], [50], [51], [50], [52], [53], [54], [55], [47], [56], [57].”
Domain Adaptation by Joint Distribution Invariant Projections (2020, result): “3 are directly cited from [71].”
A Survey of Unsupervised Deep Domain Adaptation (2018, unknown): “[125] Bayesian neural networks.”
U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps (2019, methodology): “Recently, [31] proposed a certainty method to bring two data distributions close for the domain adaption task.”