RESUMEN
Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio of MIM results in two serious problems: 1) the inadequate data utilization of images within each iteration brings prolonged pre-training, and 2) the high inconsistency of predictions results in unreliable generations, i.e., the prediction of the identical patch may be inconsistent in different mask rounds, leading to divergent semantics in the ultimately generated outcomes. To tackle these problems, we propose the efficient masked autoencoders with self-consistency (EMAE) to improve the pre-training efficiency and increase the consistency of MIM. In particular, we present a parallel mask strategy that divides the image into K non-overlapping parts, each of which is generated by a random mask with the same mask ratio. Then the MIM task is conducted parallelly on all parts in an iteration and the model minimizes the loss between the predictions and the masked patches. Besides, we design the self-consistency learning to further maintain the consistency of predictions of overlapping masked patches among parts. Overall, our method is able to exploit the data more efficiently and obtains reliable representations. Experiments on ImageNet show that EMAE achieves the best performance on ViT-Large with only 13% of MAE pre-training time using NVIDIA A100 GPUs. After pre-training on diverse datasets, EMAE consistently obtains state-of-the-art transfer ability on a variety of downstream tasks, such as image classification, object detection, and semantic segmentation.
RESUMEN
Synapses serve as the points of communication between neurons, consisting primarily of three components: the presynaptic membrane, synaptic cleft, and postsynaptic membrane. They transmit signals through the release and reception of neurotransmitters. Synaptic plasticity, the ability of synapses to undergo structural and functional changes, is influenced by proteins such as growth-associated proteins, synaptic vesicle proteins, postsynaptic density proteins, and neurotrophic growth factors. Furthermore, maintaining synaptic plasticity consumes more than half of the brain's energy, with a significant portion of this energy originating from ATP generated through mitochondrial energy metabolism. Consequently, the quantity, distribution, transport, and function of mitochondria impact the stability of brain energy metabolism, thereby participating in the regulation of fundamental processes in synaptic plasticity, including neuronal differentiation, neurite outgrowth, synapse formation, and neurotransmitter release. This article provides a comprehensive overview of the proteins associated with presynaptic plasticity, postsynaptic plasticity, and common factors between the two, as well as the relationship between mitochondrial energy metabolism and synaptic plasticity.
Asunto(s)
Sinapsis , Transmisión Sináptica , Sinapsis/fisiología , Transmisión Sináptica/fisiología , Mitocondrias/metabolismo , Plasticidad Neuronal/fisiología , AutofagiaRESUMEN
OBJECTIVE: The aim of this study was to systematically evaluate the therapeutic effects of Dihuang Yinzi decoction on Alzheimer's disease (AD) and provide a medical evidence-based clinical application of traditional Chinese medicine (TCM). METHODS: A comprehensive search was conducted across multiple databases, including PubMed, Embase, Cochrane Library, China National Journals Full-text Database, VIP Database for Chinese Technical Periodicals, Wan Fang database, and SinoMed database, to collect clinical randomized controlled trials of Dihuang Yinzi decoction in the treatment of AD. Strict literature screening was performed based on predefined inclusion and exclusion criteria. The Cochrane Collaboration risk of bias assessment tool and the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) system recommendation-level method was used to assess the quality of the included studies. Review Manager 5.4 and Stata 17 software were used for data synthesis and processing, while GRADE Profiler 3.6 software was used to evaluate the quality of evidence for outcome indicators (risk ratio, standardized mean difference, and weighted mean difference). RESULTS: A total of 11 studies involving 798 patients met the inclusion criteria. Dihuang Yinzi decoction, whether used alone or in combination with conventional Western medicine, demonstrated superior efficacy compared to conventional Western medicine alone in improving the clinical effective rate, TCM syndrome score, activity of daily living score, Mini-Mental State Examination score, and Hasegawa Dementia Scale score in AD treatment. Furthermore, it exhibited a favorable safety profile. However, the GRADE evidence quality rating for the included studies was low. CONCLUSIONS: Dihuang Yinzi decoction, either used alone or in combination with conventional Western medicine, shows promising results in enhancing cognitive and memory functions as well as the self-care ability of patients with AD. However, the low GRADE evidence quality rating highlights the need for focused advancements in the planning and execution of clinical randomized controlled trials during future research attempts.
Asunto(s)
Enfermedad de Alzheimer , Medicina , Humanos , Enfermedad de Alzheimer/tratamiento farmacológico , Resultado del Tratamiento , Medicina Tradicional China , ChinaRESUMEN
The field of object detection has made great progress in recent years. Most of these improvements are derived from using a more sophisticated convolutional neural network. However, in the case of humans, the attention mechanism, global structure information, and local details of objects all play an important role for detecting an object. In this paper, we propose a novel fully convolutional network, named as Attention CoupleNet, to incorporate the attention-related information and global and local information of objects to improve the detection performance. Specifically, we first design a cascade attention structure to perceive the global scene of the image and generate class-agnostic attention maps. Then the attention maps are encoded into the network to acquire object-aware features. Next, we propose a unique fully convolutional coupling structure to couple global structure and local parts of the object to further formulate a discriminative feature representation. To fully explore the global and local properties, we also design different coupling strategies and normalization ways to make full use of the complementary advantages between the global and local information. Extensive experiments demonstrate the effectiveness of our approach. We achieve state-of-the-art results on all three challenging data sets, i.e., a mAP of 85.7% on VOC07, 84.3% on VOC12, and 35.4% on COCO. Codes are publicly available at https://github.com/tshizys/CoupleNet.