Although the means of catching remote sensing images are becoming more effective and more abundant, the samples that can be collected in some specific environments can be quite scarce. When there are ...limited labeled samples, the methods for analyzing remote sensing images for scene classification perform drastically worse. Methods that classify few-shot remote sensing image scenes are often based on meta-learning algorithms for the handling of sparse data. However, this research shows they will be affected by supervision collapse where features in remote sensing images that help with out-of-distribution classes are discarded, which is harmful for the generation of unseen classes and new tasks. In this work, we wish to remind readers of the existence of supervision collapse in scene classification of few-shot remote sensing images and propose a method named SSMR based on multi-layer feature contrast to overcome supervision collapse. First of all, the method makes use of the label information contained in a finite number of samples for supervision and guides self-supervised learning to train the embedding network with supervision generated by multilayer feature contrast. This can prevent features from losing intra-class variation. Intra-class variation is always useful in classifying unseen data. What is more, the multi-layer feature contrast is merged with self-distillation, and the modified self-distillation is used to encourage the embedding network to extract sufficiently general features that transfer better to unseen classes and new domains. We demonstrate that most of the existing few-shot scene classification methods suffer from supervision collapse and that SSMR overcomes supervision collapse well in the experiments on the new dataset we specially designed for examining the problem, with a 2.4–17.2% increase compared to the available methods. Furthermore, we performed a series of ablation experiments to demonstrate how effective and necessary each structure of the proposed method is and to show how different choices in training impact final performance.
ABSTRACTThe training of image captioning (IC) models requires a large number of caption-labeled samples, which is usually difficult to satisfy in the actual remote sensing scenarios. The performance ...of the models will be damaged due to the few-shot problems. We describe the few-shot problems in remote sensing image captioning (RC) and design two research schemes. Then, we propose a few-shot RC framework few-shot remote sensing image captioning framework (FRIC). FRIC does not need additional samples and uses a simple base model. FRIC tries to get performance boosts from split samples and reduce the negative effects of noises. Unlike previous works that use 100% samples to simulate few-shot scenarios, FRIC uses less than 1.0% data to simulate actual few-shot scenarios. While previous works focus on improving the encoder, FRIC focuses on optimizing the decoder with parameter ensemble, multi-model ensemble and self-distillation. FRIC can train a simple base model with limited caption-labeled samples to generate captions that meet human expectations. FRIC shows obvious advantages to other methods when trained with only 0.8% samples of RC datasets. No previous work has used such a small amount of data to train the RC model. In addition, the effectiveness of the components in FRIC is verified with ablation experiments.
Display omitted
•A new deep neural network approach to reconstruct subsurface temperature.•Super-resolution of subsurface temperature from 1° to 0.25° from remote sensing.•CNN outperformed LightGBM ...in the case of big training samples.•Higher-resolution data support for global ocean warming and internal variability study.
Subsurface ocean observations are sparse and insufficient, significantly constraining studies of ocean processes. Retrieving high-resolution subsurface dynamic parameters from remote sensing observations using specific inversion models is possible but challenging. This study proposed two kinds of machine learning algorithms, namely, Convolutional Neural Network (CNN) and Light Gradient Boosting Machine (LightGBM), to reconstruct the subsurface temperature (ST) of the ocean’s upper 1000 m with a high resolution of 0.25° based on the satellite-based sea surface parameters combined with Argo float and EN4 profile data. We managed to improve the spatial resolution of ST from 1° to 0.25°. We employed two machine learning algorithms to set up monotemporal models of the four seasons and time-series models and adopted the determination coefficient (R2) and Root Mean Squared Error (RMSE) to evaluate the models’ prediction accuracy. The results show that LightGBM outperformed CNN in the case of small training samples. By contrast, in the case of big training samples, CNN outperformed LightGBM. Meanwhile, the ST with a high resolution of 0.25° predicted by the time-series CNN model can better observe mesoscale phenomena. This study provides more useful and higher-resolution data support for further studies on the warming and variability of the ocean interior under global warming.
Upon blood vessel injury, platelets are exposed to adhesive proteins in the vascular wall and soluble agonists, which initiate platelet activation, leading to formation of hemostatic thrombi. ...Pathological activation of platelets can induce occlusive thrombosis, resulting in ischemic events such as heart attack and stroke, which are leading causes of death globally. Platelet activation requires intracellular signal transduction initiated by platelet receptors for adhesion proteins and soluble agonists. Whereas many platelet activation signaling pathways have been established for many years, significant recent progress reveals much more complex and sophisticated signaling and amplification networks. With the discovery of new receptor signaling pathways and regulatory networks, some of the long-standing concepts of platelet signaling have been challenged. This review provides an overview of the new developments and concepts in platelet activation signaling.
Cadmium (Cd) pollution in food chains pose a potential health risk for humans. Sulfur (S) is a significant macronutrient that plays a significant role in the regulation of plant responses to diverse ...biotic and abiotic stresses. However, no information is currently available about the impact of S application on ascorbate-glutathione metabolism (ASA-GSH cycle) of Pakchoi plants under Cd stress. The two previously identified genotypes, namely, Aikangqing (a Cd-tolerant cultivar) and Qibaoqing (a Cd-sensitive cultivar), were utilized to investigate the role of S to mitigate Cd toxicity in Pakchoi plants under different Cd regimes. Results showed that Cd stress inhibited plant growth and induced oxidative stress. Exogenous application of S significantly increased the tolerance of Pakchoi seedlings suffering from Cd stress. This effect was demonstrated by increased growth parameters; stimulated activities of the antioxidant enzymes and upregulated genes involved in the ASA-GSH cycle and S assimilation; and by the enhanced ASA, GSH, phytochelatins, and nonprotein thiol production. This study shows that applying S nutrition can mitigate Cd toxicity in Pakchoi plants which has the potential in assisting the development of breeding strategies aimed at limiting Cd phytoaccumulation and decreasing Cd hazards in the food chain.
The electrification of vehicle helps to improve its operation efficiency and safety. Due to fast development of network, sensors, as well as computing technology, it becomes realizable to have ...vehicles driving autonomously. To achieve autonomous driving, several steps, including environment perception, path-planning, and dynamic control, need to be done. However, vehicles equipped with on-board sensors still have limitations in acquiring necessary environmental data for optimal driving decisions. Intelligent and connected vehicles (ICV) cloud control system (CCS) has been introduced as a new concept as it is a potentially synthetic solution for high level automated driving to improve safety and optimize traffic flow in intelligent transportation. This paper systematically investigated the concept of cloud control system from cloud related applications on ICVs, and cloud control system architecture design, as well as its core technologies development. Based on the analysis, the challenges and suggestions on cloud control system development have been addressed.
How cells sense their mechanical environment and transduce forces into biochemical signals is a crucial yet unresolved question in mechanobiology. Platelets use receptor glycoprotein Ib (GPIb), ...specifically its α subunit (GPIbα), to signal as they tether and translocate on von Willebrand factor (VWF) of injured arterial surfaces against blood flow. Force elicits catch bonds to slow VWF-GPIbα dissociation and unfolds the GPIbα leucine-rich repeat domain (LRRD) and juxtamembrane mechanosensitive domain (MSD). How these mechanical processes trigger biochemical signals remains unknown. Here we analyze these extracellular events and the resulting intracellular Ca(2+) on a single platelet in real time, revealing that LRRD unfolding intensifies Ca(2+) signal whereas MSD unfolding affects the type of Ca(2+) signal. Therefore, LRRD and MSD are analog and digital force transducers, respectively. The >30 nm macroglycopeptide separating the two domains transmits force on the VWF-GPIbα bond (whose lifetime is prolonged by LRRD unfolding) to the MSD to enhance its unfolding, resulting in unfolding cooperativity at an optimal force. These elements may provide design principles for a generic mechanosensory protein machine.
Large-scale caption-labeled remote sensing image samples are expensive to acquire, and the training samples available in practical application scenarios are generally limited. Therefore, remote ...sensing image caption generation tasks will inevitably fall into the dilemma of few-shot, resulting in poor qualities of the generated text descriptions. In this study, we propose a self-learning method named SFRC for few-shot remote sensing image captioning. Without relying on additional labeled samples and external knowledge, SFRC improves the performance in few-shot scenarios by ameliorating the way and efficiency of the method of learning on limited data. We first train an encoder for semantic feature extraction using a supplemental modified BYOL self-supervised learning method on a small number of unlabeled remote sensing samples, where the unlabeled remote sensing samples are derived from caption-labeled samples. When training the model for caption generation in a small number of caption-labeled remote sensing samples, the self-ensemble yields a parameter-averaging teacher model based on the integration of intermediate morphologies of the model over a certain training time horizon. The self-distillation uses the self-ensemble-obtained teacher model to generate pseudo labels to guide the student model in the next generation to achieve better performance. Additionally, when optimizing the model by parameter back-propagation, we design a baseline incorporating self-critical self-ensemble to reduce the variance during gradient computation and weaken the effect of overfitting. In a range of experiments only using limited caption-labeled samples, the performance evaluation metric scores of SFRC exceed those of recent methods. We conduct percentage sampling few-shot experiments to test the performance of the SFRC method in few-shot remote sensing image captioning with fewer samples. We also conduct ablation experiments on key designs in SFRC. The results of the ablation experiments prove that these self-learning designs we generated for captioning in sparse remote sensing sample scenarios are indeed fruitful, and each design contributes to the performance of the SFRC method.
Mitogen-activated protein kinases (MAPK), p38, and extracellular stimuli-responsive kinase (ERK), are acutely but transiently activated in platelets by platelet agonists, and the agonist-induced ...platelet MAPK activation is inhibited by ligand binding to the integrin αIIbβ3. Here we show that, although the activation of MAPK, as indicated by MAPK phosphorylation, is initially inhibited after ligand binding to integrin αIIbβ3, integrin outside-insignaling results in a late but sustained activation of MAPKs in platelets. Furthermore, we show that the early agonist-induced MAPK activation and the late integrin-mediated MAPK activation play distinct roles in different stages of platelet activation. Agonist-induced MAPK activation primarily plays an important role in stimulating secretion of platelet granules, while integrin-mediated MAPK activation is important in facilitating clot retraction. The stimulatory role of MAPK in clot retraction is mediated by stimulating myosin light chain (MLC) phosphorylation. Importantly, integrin-dependent MAPK activation, MAPK-dependent MLC phosphorylation, and clot retraction are inhibited by a Rac1 inhibitor and in Rac1 knockout platelets, indicating that integrin-induced activation of MAPK and MLC and subsequent clot retraction is Rac1-dependent. Thus, our results reveal 2 different activation mechanisms of MAPKs that are involved in distinct aspects of platelet function and a novel Rac1-MAPK–dependent cell retractile signaling pathway.
Integrins mediate cell adhesion to the extracellular matrix and transmit signals within the cell that stimulate cell spreading, retraction, migration, and proliferation. The mechanism of integrin ...outside-in signaling has been unclear. We found that the heterotrimeric guanine nucleotide-binding protein (G protein), Gα
13
, directly bound to the integrin β
3
cytoplasmic domain, and that Gα
13
-integrin interaction was promoted by ligand binding to the integrin α
IIb
β
3
and by guanosine triphosphate (GTP)-loading of Gα
13
. Interference of Gα
13
expression or a myristoylated fragment of Gα
13
that inhibited interaction of α
IIb
β
3
with Gα
13
diminished activation of protein kinase c-Src and stimulated the small GTPase RhoA, consequently inhibiting cell spreading and accelerating cell retraction. We conclude that integrins are non-canonical Gα
13
-coupled receptors that provide a mechanism for dynamic regulation of RhoA.