RESUMO
The majority of existing works explore Unsupervised Domain Adaptation (UDA) with an ideal assumption that samples in both domains are available and complete. In real-world applications, however, this assumption does not always hold. For instance, data-privacy is becoming a growing concern, the source domain samples may be not publicly available for training, leading to a typical Source-Free Domain Adaptation (SFDA) problem. Traditional UDA methods would fail to handle SFDA since there are two challenges in the way: the data incompleteness issue and the domain gaps issue. In this paper, we propose a visually SFDA method named Adversarial Style Matching (ASM) to address both issues. Specifically, we first train a style generator to generate source-style samples given the target images to solve the data incompleteness issue. We use the auxiliary information stored in the pre-trained source model to ensure that the generated samples are statistically aligned with the source samples, and use the pseudo labels to keep semantic consistency. Then, we feed the target domain samples and the corresponding source-style samples into a feature generator network to reduce the domain gaps with a self-supervised loss. An adversarial scheme is employed to further expand the distributional coverage of the generated source-style samples. The experimental results verify that our method can achieve comparative performance even compared with the traditional UDA methods with source samples for training.
RESUMO
Metal nanoclusters are excellent electrochemiluminescent luminophores owing to their rich electrochemical and optical properties. However, the optical activity of their electrochemiluminescence (ECL) is unknown. Herein, we achieved, for the first time, the integration of optical activity and ECL, i.e., circularly polarized electrochemiluminescence (CPECL), in a pair of chiral Au9Ag4 metal nanocluster enantiomers. Chiral ligand induction and alloying were employed to endow the racemic nanoclusters with chirality and photoelectrochemical reactivity. S-Au9Ag4 and R-Au9Ag4 exhibited chirality and bright-red emission (quantum yield = 4.2%) in the ground and excited states. The enantiomers showed mirror-imaged CPECL signals at 805 nm owing to their highly intense and stable ECL emission in the presence of tripropylamine as a co-reactant. The ECL dissymmetry factor of the enantiomers at 805 nm was calculated to be ±3 × 10-3, which is comparable with that obtained from their photoluminescence. The obtained nanocluster CPECL platform shows the discrimination of chiral 2-chloropropionic acid. The integration of optical activity and ECL in metal nanoclusters provides the opportunity to achieve enantiomer discrimination and local chirality detection with high sensitivity and contrast.
RESUMO
Prevalent domain adaptation approaches are suitable for a close-set scenario where the source domain and the target domain are assumed to share the same data categories. However, this assumption is often violated in real-world conditions where the target domain usually contains samples of categories that are not presented in the source domain. This setting is termed as open set domain adaptation (OSDA). Most existing domain adaptation approaches do not work well in this situation. In this article, we propose an effective method, named joint alignment and category separation (JACS), for OSDA. Specifically, JACS learns a latent shared space, where the marginal and conditional divergence of feature distributions for commonly known classes across domains is alleviated (Joint Alignment), the distribution discrepancy between the known classes and the unknown class is enlarged, and the distance between different known classes is also maximized (Category Separation). These two aspects are unified into an objective to reinforce the optimization of each part simultaneously. The classifier is achieved based on the learned new feature representations by minimizing the structural risk in the reproducing kernel Hilbert space. Extensive experiment results verify that our method outperforms other state-of-the-art approaches on several benchmark datasets.
RESUMO
Zero-shot learning (ZSL) is a pretty intriguing topic in the computer vision community since it handles novel instances and unseen categories. In a typical ZSL setting, there is a main visual space and an auxiliary semantic space. Most existing ZSL methods handle the problem by learning either a visual-to-semantic mapping or a semantic-to-visual mapping. In other words, they investigate a unilateral connection from one end to the other. However, the connection between the visual space and the semantic space are bilateral in reality, that is, the visual space depicts the semantic space; the semantic space, on the other hand, describes the visual space. In this article, therefore, we investigate the bilateral connections in ZSL and present a novel model, called Boomerang-GAN, by taking advantage of conditional generative adversarial networks (GANs). Specifically, we generate unseen visual samples from their category semantic embeddings by a conditional GAN. Different from the existing generative ZSL methods that only consider generating visual features from class descriptions, our method also considers that the generated visual features can be translated back to their corresponding semantic embeddings by introducing a multimodal cycle-consistent loss. Extensive experiments of both ZSL and generalized ZSL on five widely used datasets verify that our method is able to outperform previous state-of-the-art approaches in both recognition and segmentation tasks.
Assuntos
Aprendizado de Máquina , SemânticaRESUMO
AIM: Currently, drugs for the treatment of diabetic nephropathy (DN) are lacking. This study aimed to explore the protective effect of crocin on DN. MAIN METHODS: Diabetes was induced in rats by streptozotocin (STZ), and changes in metabolism and renal parameters after crocin treatment were measured. Dihydroethidium (DHE) fluorescence and superoxide generation were used to detect the levels of reactive oxygen species (ROS) in rat renal tissues. Enzyme-linked immunosorbent assay was used to measure changes inflammation-related factors with crocin treatment. In addition, the expression of Nod-like receptor family pyrin domain-containing 3 (NLRP3) signaling pathway components was detected by western blot analysis, qRT-PCR, and immunohistochemistry. KEY FINDINGS: Crocin lowered blood sugar, increased serum insulin levels, and improved diabetes-related symptoms, including kidney dysfunction. Masson trichrome staining revealed that crocin could improve renal tissue fibrosis caused by hyperglycemia. Moreover, crocin inhibited ROS production in renal tissues and generally inhibited the production of the proinflammatory factors TNF-α, IL-1ß, and IL-18. Crocin exerted these functions by inhibiting the expression of the NLRP3 inflammasome in DN rats. SIGNIFICANCE: Crocin alleviates DN related oxidative stress and inflammation by inhibiting NLRP3 inflammasomes. Our results provide a new target for the treatment of DN.
Assuntos
Anti-Inflamatórios/farmacologia , Antioxidantes/farmacologia , Carotenoides/farmacologia , Nefropatias Diabéticas/tratamento farmacológico , Inflamação/tratamento farmacológico , Proteína 3 que Contém Domínio de Pirina da Família NLR/antagonistas & inibidores , Estresse Oxidativo/efeitos dos fármacos , Animais , Nefropatias Diabéticas/complicações , Nefropatias Diabéticas/metabolismo , Inflamassomos/antagonistas & inibidores , Inflamassomos/metabolismo , Inflamação/complicações , Inflamação/metabolismo , Masculino , Proteína 3 que Contém Domínio de Pirina da Família NLR/metabolismo , Ratos Sprague-DawleyRESUMO
Domain adaptation is suitable for transferring knowledge learned from one domain to a different but related domain. Considering the substantially large domain discrepancies, learning a more generalized feature representation is crucial for domain adaptation. On account of this, we propose an adaptive component embedding (ACE) method, for domain adaptation. Specifically, ACE learns adaptive components across domains to embed data into a shared domain-invariant subspace, in which the first-order statistics is aligned and the geometric properties are preserved simultaneously. Furthermore, the second-order statistics of domain distributions is also aligned to further mitigate domain shifts. Then, the aligned feature representation is classified by optimizing the structural risk functional in the reproducing kernel Hilbert space (RKHS). Extensive experiments show that our method can work well on six domain adaptation benchmarks, which verifies the effectiveness of ACE.
RESUMO
Domain adaptation tackles the problem where the training source domain and the test target domain have distinctive data distributions, and therefore improves the generalization ability of deep models. The very popular mechanism of domain adaptation is to learn a new feature representation which is supposed to be domain-invariant, so that the classifiers trained on the source domain can be directly applied to the target domain. However, recent work reveals that learning new feature representations may potentially deteriorate the adaptability of the original features and increase the expected error bound of the target domain. To address this, we propose to adapt classifiers rather than features. Specifically, we fill in the distribution gaps between domains by some additional transferable representations which are explicitly learned from the original features while keeping the original features unchanged. In addition, we argue that transferable representations should be able to be translated from one domain to the other with appropriate mappings. At the same time, we introduce conditional entropy to mitigate the semantic confusion during mapping. Experiments on both standard and large-scale datasets verify that our method is able to achieve the new state-of-the-art results on unsupervised domain adaptation.
Assuntos
Aprendizado de Máquina/normasRESUMO
Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly labeled target domain. A majority of existing works transfer the knowledge at either feature level or sample level. Recent studies reveal that both of the paradigms are essentially important, and optimizing one of them can reinforce the other. Inspired by this, we propose a novel approach to jointly exploit feature adaptation with distribution matching and sample adaptation with landmark selection. During the knowledge transfer, we also take the local consistency between the samples into consideration so that the manifold structures of samples can be preserved. At last, we deploy label propagation to predict the categories of new instances. Notably, our approach is suitable for both homogeneous- and heterogeneous-domain adaptations by learning domain-specific projections. Extensive experiments on five open benchmarks, which consist of both standard and large-scale datasets, verify that our approach can significantly outperform not only conventional approaches but also end-to-end deep models. The experiments also demonstrate that we can leverage handcrafted features to promote the accuracy on deep features by heterogeneous adaptation.
RESUMO
A series of CuNiFe layered double hydroxides (LDHs) with various Cu/Ni molar ratios were synthesized as catalysts for Fenton degradation of phenol. It is found that Cu+, Cu2+, Ni2+, Ni3+ and Fe3+ are present on LDHs, owing to an electron transfer from Ni2+ to Cu2+ via metal-oxo-metal bridges. At lower Cu/Ni ratios, the highly dispersed MO6 octahedra and the electron donation effect of Ni facilitate such electron transfer and thus increase the percentage of Cu+. The catalytic activity increases with the decrease in Cu/Ni ratio. The most active Cu0.5Ni2.5Fe LDH can mineralize 98.9% phenol at ambient pH and less excessive H2O2 dosage ( [Formula: see text] /Mphenolâ¯=â¯37). Even at the H2O2 dosage close to the theoretical value, around 90% phenol can be mineralized. The structure-activity correlation indicates Cu+ which can readily react with H2O2 to produce hydroxyl radicals may dominate the reaction. The regeneration of Cu+ could be achieved by the electron transfer between Cu2+ and Ni2+ in LDHs. Moreover, Fe3+ can also act as Fenton-like active sites. The special structure of CuNiFe LDHs could offer surface-enriched and easily regenerated Cu+ species, leading to the complete mineralization of phenol and the efficient use of H2O2.