LSDT: Latent Sparse Domain Transfer Learning for Visual Adaptation

230 citations recorded by the source corpus.

How researchers see this paper

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

Towards more Reliable Transfer Learning (2018, background): “earning [23] addresses the challenge of data scarcity in the target domain by utilizing labeled data from other related source domain(s). Plenty of research has been done on the single-source setting [25,22,35], and it has been shown that transfer learning has a wide range of applications in areas s”
Domain Adaptation by Joint Distribution Invariant Projections (2020, methodology): “Notable examples include, but are not limited to, methods based on linear discriminant analysis [7], reconstruction [48]–[50], and metric learning [51].”
Multi-Adversarial Faster-RCNN for Unrestricted Object Detection (2019, background): “Domain adaptation aims to bridge different domains or tasks by reducing the distribution discrepancy, which has been a focus in various computer vision tasks [15, 22, 23, 37, 38].”
Transfer Learning via Learning to Transfer (2018, methodology): “Common Latent Space Based This line of algorithms, including but not limited to TCA (Pan et al., 2011), LS-DT (Zhang et al., 2016), and DIP (Baktashmotlagh et al., 2013), assumes that domain-invariant feature factors lie in a single shared latent space.”