Comprehensive mining of information in Weakly Supervised Semantic Segmentation: Saliency semantics and edge semantics.

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. The network learns feature representations consistent with salient regions via the proposed pixel-level class-agnostic distance loss. Then, the full saliency semantic information is mined by explicitly receiving pixel-level feedback. The initial pseudo-label with complete saliency semantic information can be obtained after the first stage. In the second stage, we focus on the mining of edge semantic information through the proposed edge semantic mining module. Specifically, we guide the initial pseudo-label avoid learning about false semantic information and obtain high-confidence edge semantics. The self-correction ability of the segmentation network is also fully utilized to obtain more edge semantic information. Extensive experiments are conducted on the PASCAL VOC 2012 and MS COCO 2014 datasets to verify the feasibility and superiority of this approach.

Mask-Shift-Inference: A novel paradigm for domain generalization.

Domain Generalization (DG) focuses on the Out-Of-Distribution (OOD) generalization, which is able to learn a robust model that generalizes the knowledge acquired from the source domain to the unseen target domain. However, due to the existence of the domain shift, domain-invariant representation learning is challenging. Guided by fine-grained knowledge, we propose a novel paradigm Mask-Shift-Inference (MSI) for DG based on the architecture of Convolutional Neural Networks (CNN). Different from relying on a series of constraints and assumptions for model optimization, this paradigm novelly shifts the focus to feature channels in the latent space for domain-invariant representation learning. We put forward a two-branch working mode of a main module and multiple domain-specific sub-modules. The latter can only achieve good prediction performance in its own specific domain but poor predictions in other source domains, which provides the main module with the fine-grained knowledge guidance and contributes to the improvement of the cognitive ability of MSI. Firstly, during the forward propagation of the main module, the proposed MSI accurately discards unstable channels based on spurious classifications varying across domains, which have domain-specific prediction limitations and are not conducive to generalization. In this process, a progressive scheme is adopted to adaptively increase the masking ratio according to the training progress to further reduce the risk of overfitting. Subsequently, our paradigm enters the compatible shifting stage before the formal prediction. Based on maximizing semantic retention, we implement the domain style matching and shifting through the simple transformation through Fourier transform, which can explicitly and safely shift the target domain back to the source domain whose style is closest to it, requiring no additional model updates and reducing the domain gap. Eventually, the paradigm MSI enters the formal inference stage. The updated target domain is predicted in the main module trained in the previous stage with the benefit of familiar knowledge from the nearest source domain masking scheme. Our paradigm is logically progressive, which can intuitively exclude the confounding influence of domain-specific spurious information along with mitigating domain shifts and implicitly perform semantically invariant representation learning, achieving robust OOD generalization. Extensive experimental results on PACS, VLCS, Office-Home and DomainNet datasets verify the superiority and effectiveness of the proposed method.

Study on Magnetic Control Systems of Micro-Robots.

Magnetic 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. Furthermore, aiming at surmounting the instability of magnetic control system, we utilize SolidWorks2020 software to partially modify the SAMM system to make its final overall thickness attain 111 mm, which is capable to control and observe the motion of the micro-robot under the microscope system in an even better fashion. Ultimately, we emphasize the challenges and open problems that urgently need to be settled, and summarize the direction of development in this field, which plays a momentous role in the wide and safe application of magnetic control systems of micro-robots in clinic.