عنوان البحث | ملخص البحث | Research Abstract |
Behavior regularized prototypical networks for semi-supervised few-shot image classification | | We propose a Behavior Regularized Prototypical Network (BR-ProtoNet) for few-shot image classification in semi-supervised scenarios. To learn a generalizable metric, we exploit readily-available unlabeled data and construct complementary co |
KTransGAN: Variational Inference-Based Knowledge Transfer for Unsupervised Conditional Generative Learning | | Class-conditional generative models have gained popularity due to their characteristics of learning disentangled representations. However, these models typically require labeled examples in training. In this paper, we explore the feasibilit |
Knowledge Exchange Between Domain-Adversarial and Private Networks Improves Open Set Image Classification | | Both target-specific and domain-invariant features can facilitate Open Set Domain Adaptation (OSDA). To exploit these features, we propose a Knowledge Exchange (KnowEx) model which jointly trains two complementary constituent networks: (1) |
Adversarially Smoothed Feature Alignment for Visual Domain Adaptation | | Recent approaches to unsupervised domain adaptation focus on transferring knowledge from source (labeled) data to target (unlabeled) data. Both data types share the same class space but originate from different domains. One way to achieve t |
Unsupervised Domain Adaptation VIA Cluster Alignment with Maximum Classifier Discrepancy | | One way of addressing the problem of unsupervised domain adaptation (UDA) is to perform adversarial training between two classifiers and their shared feature extractor. The two classifiers are enforced to detect the misaligned regions betwe |
Adversarially Constrained Interpolation for Unsupervised Domain Adaptation | | We address the problem of unsupervised domain adaptation (UDA) which aims at adapting models trained on a labeled domain to a completely unlabeled domain. One way to achieve this goal is to learn a domain-invariant representation. However, |
Semi-Supervised Pedestrian Instance Synthesis and Detection With Mutual Reinforcement | | We propose a GAN-based scene-specific instance synthesis and classification model for semi-supervised pedestrian detection. Instead of collecting unreliable detections from unlabeled data, we adopt a class-conditional GAN for synthesizing p |