Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, or attention mechanisms. These methods, however, incur unfavorable latency during inference, and the performance saturates over the past few years. In this paper, we present a novel perspective on this task. We notice that detailed local geometrical information probably is not the key to point cloud analysis -we introduce a pure residual MLP network, called PointMLP, which integrates no "sophisticated" local geometrical extractors but still performs very competitively. Equipped with a proposed lightweight geometric affine module, PointMLP delivers the new stateof-the-art on multiple datasets. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. We emphasize that PointMLP achieves this strong performance without any sophisticated operations, hence leading to a superior inference speed. Compared to most recent CurveNet, PointMLP trains 2× faster, tests 7× faster, and is more accurate on ModelNet40 benchmark. We hope our PointMLP may help the community towards a better understanding of point cloud analysis. The code is available at https://github.com/ma-xu/pointMLP-pytorch.

No abstract

A new monosesquiterpene diacetylgliocladic acid (1), a new dimeric sesquiterpene divirensol H (9), and two exceptionally novel trimeric sesquiterpene trivirensols A and B (11 and 12), together with another eight known congeners, were purified from an endophytic fungus Trichoderma virens FY06, derived from Litchi chinensis Sonn. whose fruit is a delicious and popular food. All of them were identified by comprehensive spectroscopic analysis, combined with biosynthetic considerations. Trivirensols A and B are unprecedented trimers of which three subunits are connected by two ester bonds of the sesquiterpene class. Relative to the positive control triadimefon, all the tested metabolites showed strong inhibitory activities against at least one phytopathogenic fungus among Penicillium italicum, Fusarium oxysporum, Fusarium graminearum, Colletotrichum musae, and Colletotrictum gloeosporioides. Notably, as metabolites of the endophytic fungus from L. chinensis, they all presented strong antifungal activities against C. gloeosporioides which causes anthracnose in L. chinensis.

Because there are many unlabeled samples in hyperspectral images and the cost of manual labeling is high, this paper adopts semi-supervised learning method to make full use of many unlabeled samples. In addition, those hyperspectral images contain much spectral information and the convolutional neural networks have great ability in representation learning. This paper proposes a novel semi-supervised hyperspectral image classification framework which utilizes self-training to gradually assign highly confident pseudo labels to unlabeled samples by clustering and employs spatial constraints to regulate self-training process. Spatial constraints are introduced to exploit the spatial consistency within the image to correct and re-assign the mistakenly classified pseudo labels. Through the process of self-training, the sample points of high confidence are gradually increase, and they are added to the corresponding semantic classes, which makes semantic constraints gradually enhanced. At the same time, the increase in high confidence pseudo labels also contributes to regional consistency within hyperspectral images, which highlights the role of spatial constraints and improves the HSIc efficiency. Extensive experiments in HSIc demonstrate the effectiveness, robustness, and high accuracy of our approach.

Current adversarial adaptation methods attempt to align the cross-domain features whereas two challenges remain unsolved: 1) conditional distribution mismatch between different domains and 2) the bias of decision boundary towards the source domain. To solve these challenges, we propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures (UODA). UODA consists of a generator and two classifiers (i.e., the source-based and the target-based classifiers respectively) which are trained with opposite forms of losses for a unified object. The target-based classifier attempts to cluster the target features to improve intra-class density and enlarge inter-class divergence. Meanwhile, the sourcebased classifier is designed to scatter the source features to enhance the smoothness of decision boundary. Through the alternation of source-feature expansion and target-feature clustering procedures, the target features are well-enclosed within the dilated boundary of the corresponding source features. This strategy effectively makes the cross-domain features precisely aligned. To overcome the model collapse through training, we progressively update the measurement of distance and the feature representation on both domains via an adversarial training paradigm. Extensive experiments on the benchmarks of DomainNet and Office-home datasets demonstrate the effectiveness of our approach over the state-of-the-art method.