Attending to Discriminative Certainty for Domain Adaptation

Abstract

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 specify 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.

arXiv commentCVPR 2019 Accepted, Project: https://delta-lab-iitk.github.io/CADA/

References in corpus (14)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Deep Visual Domain Adaptation: A Survey
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
• Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
• Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
• Adversarial Adaptation of Scene Graph Models for Understanding Civic Issues

Cited by in corpus (4)

• Unsupervised Domain Adaptation by Uncertain Feature Alignment
• Bi-Directional Generation for Unsupervised Domain Adaptation
• Adversarial Incremental Learning
• Uncertainty based Class Activation Maps for Visual Question Answering