Publications by authors named "Youjia Shao"
Article Synopsis
- - Domain Generalization (DG) aims to create robust models that can generalize knowledge from known source domains to unseen target domains, but challenges arise due to domain shifts that complicate the learning of domain-invariant representations.
- - The proposed Mask-Shift-Inference (MSI) paradigm leverages Convolutional Neural Networks (CNNs) by focusing on feature channels in the latent space, using a two-branch structure with a main module and domain-specific sub-modules to enhance model generalization and cognitive ability.
- - MSI implements a two-step process: first, it selectively discards unstable channels during forward propagation to minimize overfitting, and second, it employs Fourier transform for domain style matching, allowing it to effectively
In the studies of Weakly Supervised Semantic Segmentation (WSSS) with image-level labels, there is an issue of incomplete semantic information, which we summarize as insufficient saliency semantic mining and neglected edge semantics. We proposes a two-stage framework, Saliency Semantic Full Mining-Edge Semantic Mining (SSFM-ESM), which views WSSS from the perspective of comprehensive information mining. In the first stage, we rely on SSFM to address the insufficient saliency semantic mining.
View Article and Find Full Text PDFMagnetic control systems of micro-robots have recently blossomed as one of the most thrilling areas in the field of medical treatment. For the sake of learning how to apply relevant technologies in medical services, we systematically review pioneering works published in the past and divide magnetic control systems into three categories: stationary electromagnet control systems, permanent magnet control systems and mobile electromagnet control systems. Based on this, we ulteriorly analyze and illustrate their respective strengths and weaknesses.
View Article and Find Full Text PDF