SAAF: Self-Adaptive Attention Factor-Based Taylor-Pruning on Convolutional Neural Networks.

Nowadays, pruning techniques have drawn attention to convolutional neural networks (CNNs) for reducing the consumption of computation resources. In particular, the Taylor-based method simplifies the evaluation of importance for each filter as the product of the gradient and weight value of the output features, which outperforms other methods in reductions of parameters and floating point operations (FLOPs). However, the Taylor-based method sacrifices too much accuracy when the overall pruning rate is relatively large compared with other pruning algorithms. In this article, we propose a self-adaptive attention factor (SAAF) to improve the performance of the slimmed model when conventional Taylor-based pruning is utilized under higher pruning. Specifically, SAAF can be calculated by leveraging the remaining ratio of filters at the early pruning stage of the Taylor-based method, and then, some pruned filters can be recovered for improving the accuracy of the slimmed model in terms of SAAF. It means that SAAF can protect filters from being overslimmed to eliminate the degeneration of Taylor-based pruning when the pruning rate is large as well as can compress models apparently across various datasets. We test the efficiency of SAAF on VGG-16 and ResNet-50 with CIFAR-10, Tiny-ImageNet, ImageNet-1000, and remote sensing images. Our method outperforms the traditional Taylor-based method obviously in accuracy, and there are only tiny sacrifices in the reduction of parameters and FLOPs, which is better than other pruning methods.

Few-Shot Learning With Enhancements to Data Augmentation and Feature Extraction.

The few-shot image classification task is to enable a model to identify novel classes by using only a few labeled samples as references. In general, the more knowledge a model has, the more robust it is when facing novel situations. Although directly introducing large amounts of new training data to acquire more knowledge is an attractive solution, it violates the purpose of few-shot learning with respect to reducing dependence on big data. Another viable option is to enable the model to accumulate knowledge more effectively from existing data, i.e., improve the utilization of existing data. In this article, we propose a new data augmentation method called self-mixup (SM) to assemble different augmented instances of the same image, which facilitates the model to more effectively accumulate knowledge from limited training data. In addition to the utilization of data, few-shot learning faces another challenge related to feature extraction. Specifically, existing metric-based few-shot classification methods rely on comparing the extracted features of the novel classes, but the widely adopted downsampling structures in various networks can lead to feature degradation due to the violation of the sampling theorem, and the degraded features are not conducive to robust classification. To alleviate this problem, we propose a calibration-adaptive downsampling (CADS) that calibrates and utilizes the characteristics of different features, which can facilitate robust feature extraction and benefit classification. By improving data utilization and feature extraction, our method shows superior performance on four widely adopted few-shot classification datasets.

Pharmacophore-probe reaction guided purification to precisely identify electrophilic withanolides from Tubocapsicum anomalum Makino and their anti-TNBC activity.

Pharmacophore-probe reaction guided purification strategy can reduce the workload of natural product chemistry and raise the probability of obtaining undescribed and high-bioactive target compounds. In this study, a probe of N-acetyl cysteine (NAC) was used to confirm the pharmacophore of Tubocapsicum anomalum (Franch. et Sav.) Makino. Furthermore, a thiol probe named 4-bromothiophenol (BTP) guided the discovery of three undescribed (1-3) and nine known (4-12) electrophilic withanolides (EWs) featured potential anti-triple negative breast cancer (TNBC) pharmacophore. Notably, co-incubation with BTP made the single crystals of EW conjugates much more accessible, which facilitated the absolute configuration determination of EWs. Electrophilic natural products with the potential of thio-alkylation modification and covalent inhibition key proteins in tumor cell signal transduction pathways may display significant antitumor activity. The MTT results indicated that most EWs showed anti-TNBC activity and were expected to develop anti-TNBC candidate drugs with high selectivity and novel mechanism.

Structural characterization of a polysaccharide from Trametes sanguinea Lloyd with immune-enhancing activity via activation of TLR4.

A bioactive polysaccharide (TS2-2A) with a molecular weight of 15 kDa was isolated from Trametes sanguinea Lloyd, a medicinal food homologous fungus, by water extraction-alcohol precipitation and chromatographic separation. NMR analysis of polysaccharide and MS/MS analysis of its oligosaccharide indicated that TS2-2A featured a novel straight chain with a backbone of 1,3-α-d-glucopyranose and 1,4-ß-d-glucopyranose at a molar ratio of 1:4. Moreover, TS2-2A, recognized by Toll-like receptor 4 (TLR4), stimulated RAW 264.7 macrophages to release related cytokines and contributed to immune-enhancing effects. Briefly, with remarkable immune-enhancing activity and noncytotoxicity, TS2-2A was proposed to be a potential immune enhancer for supplementing drugs or functional foods.