Class-Irrelevant Feature Removal for Few-Shot Image Classification.

Most existing few-shot image classification methods employ global pooling to aggregate class-relevant local features in a data-drive manner. Due to the difficulty and inaccuracy in locating class-relevant regions in complex scenarios, as well as the large semantic diversity of local features, the class-irrelevant information could reduce the robustness of the representations obtained by performing global pooling. Meanwhile, the scarcity of labeled images exacerbates the difficulties of data-hungry deep models in identifying class-relevant regions. These issues severely limit deep models' few-shot learning ability. In this work, we propose to remove the class-irrelevant information by making local features class relevant, thus bypassing the big challenge of identifying which local features are class irrelevant. The resulting class-irrelevant feature removal (CIFR) method consists of three phases. First, we employ the masked image modeling strategy to build an understanding of images' internal structures that generalizes well. Second, we design a semantic-complementary feature propagation module to make local features class relevant. Third, we introduce a weighted dense-connected similarity measure, based on which a loss function is raised to fine-tune the entire pipeline, with the aim of further enhancing the semantic consistency of the class-relevant local features. Visualization results show that CIFR achieves the removal of class-irrelevant information by making local features related to classes. Comparison results on four benchmark datasets indicate that CIFR yields very promising performance.

Taraxacum: A Review of Ethnopharmacology, Phytochemistry and Pharmacological Activity.

Taraxacum refers to the genus Taraxacum, which has a long history of use as a medicinal plant and is widely distributed around the world. There are over 2500 species in the genus Taraxacum recorded as medicinal plants in China, Central Asia, Europe, and the Americas. It has traditionally been used for detoxification, diuresis, liver protection, the treatment of various inflammations, antimicrobial properties, and so on. We used the most typically reported Taraxacum officinale as an example and assembled its chemical makeup, including sesquiterpene, triterpene, steroids, flavone, sugar and its derivatives, phenolic acids, fatty acids, and other compounds, which are also the material basis for its pharmacological effects. Pharmacological investigations have revealed that Taraxacum crude extracts and chemical compounds contain antimicrobial infection, anti-inflammatory, antitumor, anti-oxidative, liver protective, and blood sugar and blood lipid management properties. These findings adequately confirm the previously described traditional uses and aid in explaining its therapeutic applications.

Cynanchum komarovii extract for the treatment of rheumatoid arthritis by acting on synovial cells in vitro and in vivo.

ETHNOPHARMACOLOGICAL RELEVANCE: Cynanchum komarovii (CK), the northwest Chinese region's common medicinal herb, was traditionally utilized to treat arthritis, toothache, bald sores and cholecystitis. Various forms of arthritis can be treated with CK, based on "Medicinal Plants of Chinese Desert Areas". However, the exact mechanism of action in rheumatoid arthritis (RA) is uncertain. AIM OF THE STUDY: To evaluate the in vitro and in vivo effects of CK extracts on RA and to preliminarily investigate its anti-RA mechanism of action. MATERIALS AND METHODS: The main components of CK extract were analyzed by HPLC method. The effects of CK on the proliferation and apoptosis of human rheumatoid arthritis fibroblast-like synoviocytes (HFLS-RA) cells and the expression of apoptosis-related proteins in HFLS-RA cells were evaluated by CCK8 assay, flow cytometry and WB assay. To verify the anti-RA effect of CK extracts in vivo, a collagen-induced arthritis (CIA) rat model was established. The rats were divided into six groups: normal group, model group, CK high-dose group (1000 mg/kg, CK-H), CK medium-dose group (500 mg/kg, CK-M), CK low-dose group (250 mg/kg, CK-L) and methotrexate-positive drug group (MTX); the drug was administered continuously for 28 days. Body weight changes, joint swelling, arthritis index, bone density, ankle lesions, immune organ index, splenic lesions and inflammatory factor expression were used to evaluate the in vivo anti-RA activity of the extract. RESULTS: The findings of in vitro experiments showed that 10% CK-containing serum decreased the expression level of Bcl-2, increased the expression levels of Bax and Cleaved Caspase-3 in synovial cells, and prevented TNF-α induced aberrant proliferation and apoptotic antagonism in HFLS-RA cells. According to in vivo studies, CK extract at doses above 250 mg/kg was effective in controlling the levels of inflammatory factors, lowering the arthritis index, and improving foot swelling in CIA rats. When administered at doses up to 1000 mg/kg, CK extract significantly improved synovial lesions, increased bone density, and decreased abnormally elevated immune organ index in CIA rats. CONCLUSIONS: CK has significant anti-RA activity, and its anti-RA mechanism of action may be related to the regulation of the expression levels of apoptosis related proteins and the promotion of apoptosis in synovial cells.

Imposing Semantic Consistency of Local Descriptors for Few-Shot Learning.

Few-shot learning suffers from the scarcity of labeled training data. Regarding local descriptors of an image as representations for the image could greatly augment existing labeled training data. Existing local descriptor based few-shot learning methods have taken advantage of this fact but ignore that the semantics exhibited by local descriptors may not be relevant to the image semantic. In this paper, we deal with this issue from a new perspective of imposing semantic consistency of local descriptors of an image. Our proposed method consists of three modules. The first one is a local descriptor extractor module, which can extract a large number of local descriptors in a single forward pass. The second one is a local descriptor compensator module, which compensates the local descriptors with the image-level representation, in order to align the semantics between local descriptors and the image semantic. The third one is a local descriptor based contrastive loss function, which supervises the learning of the whole pipeline, with the aim of making the semantics carried by the local descriptors of an image relevant and consistent with the image semantic. Theoretical analysis demonstrates the generalization ability of our proposed method. Comprehensive experiments conducted on benchmark datasets indicate that our proposed method achieves the semantic consistency of local descriptors and the state-of-the-art performance.

The analgesic activities of total alkaloids of the ethnic medicine Cynanchum komarovii Al. Iljinski.

ETHNOPHARMACOLOGICAL RELEVANCE: Cynanchum komarovii Al. Iljinski is a ethnomedicinal herb and this ethno-medicine is used mainly to treat arthritis, toothache, reducing phlegm, relieving cough. Total alkaloids of Cynanchum komarovii Al. Iljinski (TACKI) is the main active compound of Cynanchum komarovii Al. Iljinski. Previous investigations have revealed that TACKI can significantly inhibit rat foot swelling caused by carrageenan; it has a significant inhibitory effect on granulation tissue proliferation. Pharmacology study showed that Cynanchum komarovii Al. Iljinski has analgesia, anti-inflammatory, antibacterial, anti-tumor, relieving cough and relieving asthma. However, there is no any investigation on the mechanism of analgesia and anti-inflammation. AIM OF THE STUDY: To clarify the analgesic effect and material basis of Cynanchum komarovii Al. Iljinski, determine the analgesic effect of TACKI, and provide experimental data support for its traditional application in the treatment of various pains. MATERIALS AND METHODS: TACKI were prepared by the traditional acid extraction and alkaline precipitation method, and TACKI was analyzed through classic animal models of acute antinociceptive animal models and chronic antinociceptive. Evaluation of analgesic effects, and preliminary discussion of the mechanism of its analgesic effects were performed in this work. RESULTS: Acute toxicity experiments showed that the LD50 of TACKI mice was 2960.88 mg/kg, and symptoms of poisoning appeared. Patholog of liver and kidney studies have shown that TACKI reduces eosinophils and increases basophils in kidney glomeruli. In the study of analgesic effects, TACKI had analgesic activity through the PWL, formalin test, and acetic acid writhing test. In the chronic inflammatory antinociceptive study, the latency of the withdrawal reflex in the TACKI group was prolonged, and the mechanical withdrawal reflex threshold was significantly increased. The protein expression of NMDA, GFAP and Iba-1 in rat brain tissue can be reduced significantly byTACKI. Meanwhile, the content of TNF-α and IL-6 in rat brain tissue is reduced. CONCLUSION: TACKI has a significant analgesic activities. It may be related to inhibiting the activation of astrocytes and reducing the content of inflammatory mediators.