This paper introduces the PSA-Swin Transformer, a novel framework for image classification on small-scale datasets, highlighting the challenges of training effective models in resource-limited environments. Recognizing the limitations of current deep learning methods that rely heavily on large-scale datasets and extensive pre-training, we propose a method for handling small datasets. Our model can effectively han-dle smaller data volumes without the need for pre-training weights. The key to our approach is in the introduction of an efficient positional embedding (EPE) module, which improves parameter utilization and network expressiveness through a grouped convolutional architecture and shuffling operations for dynamic information exchange. In addition, we integrated the Polarized Self-Attention (PSA) module in Windows Multi-Head Self-Attention (W-MSA) and named the new module PSA-W-MSA; PSA addresses the complexity of learning element-specific attention by combining polarization filtering with augmentation techniques. Through a series of experiments on the Mini-Imagenet dataset, the PSA-Swin Transformer demonstrates notable performance, especially in environments where high-quality annotated data is scarce or costly to acquire. Our research results are expected to make progress in areas that require efficient and accurate image classification using limited resources.

Hyperspectral image (HSI) classification is one of the basic tasks of remote sensing image processing, which is to predict the label of each HSI pixel. Convolution neural network (CNN) and graph convolution neural network (GCN) have become the current research focus due to their outstanding performance in the field of HSI classification in recent years. However, GCN is a transductive learning method, which needs all nodes to participate in the training process to get the node embedding. Graph sample and aggregation (GraphSAGE) is an important branch of graph neural network, which can flexibly aggregate new neighbor nodes in non-Euclidean data of any structure, and capture long-range contextual relationships. Superpixel-based GraphSAGE can not only integrate the global spatial relationship of data, but also further reduce its computing cost. CNN can extract pixel-level features in a small area, and our center attention module (CAM) and center weighted convolution (CW-Conv) can also improve the feature extraction ability of CNN by enhancing the dominant position of target pixels. In order to make full use of the advantages of CNN and GraphSAGE, we propose a center weighted convolution and GraphSAGE (CW-SAGE) cooperative network for HSI classification. Specifically, graph simple and aggregate branch is constructed by superpixel-based encoder and decoder modules, then pixel-level features are extracted by a central attention convolutional neural network. Finally, the features of the two branches are spliced together for feature fusion. We conduct experiments on three hyperspectral datasets and compare the results with other current state-of-the-art methods. A series of experiments demonstrate the advantages of our method.

Events are typically composed of a sequence of subevents. Predicting a future subevent of an event is of great importance for many real-world applications. Most previous work on event prediction relied on hand-crafted features and can only predict events that already exist in the training data. In this paper, we develop an end-to-end model which directly takes the texts describing previous subevents as input and automatically generates a short text describing a possible future subevent. Our model captures the two-level sequential structure of a subevent sequence, namely, the word sequence for each subevent and the temporal order of subevents. In addition, our model incorporates the topics of the past subevents to make context-aware prediction of future subevents. Extensive experiments on a real-world dataset demonstrate the superiority of our model over several state-of-the-art methods.

Dirichlet process mixture model (DPM-M) has great potential for detecting the underlying structure of data.Extensive studies have applied it for text clustering in terms of topics.However, due to the unsupervised nature, the topic clusters are always less satisfactory.Considering that people often have some prior knowledge about which potential topics should exist in given data, we aim to incorporate such knowledge into the DPMM to improve text clustering.We propose a novel model TSDPMM based on a new seeded Pólya urn scheme.Experimental results on document clustering across three datasets demonstrate our proposed TSDPMM significantly outperforms stateof-the-art DPMM model and can be applied in a lifelong learning framework.

The success of ISOMAP depends greatly on selecting a suitable neighborhood size; however, it's an open problem how to do this efficiently. When the neighborhood size is unsuitable, shortcut edges can emerge in the neighborhood graph and shorten the involved shortest path lengths greatly, which makes them not approximate the corresponding geodesic distances anymore, that is, there doesn't exist such an approximately monotonically increasing relationship between them anymore. Based on this observation, in the paper, we use costs over the minimal connected neighborhood graph to approximate the corresponding geodesic distances, and then present an efficient method to judge whether a neighborhood size is suitable beforehand, by which a suitable neighborhood size can be selected more efficiently than the straightforward method with the residual variance. Besides, the correctness of the intrinsic dimensionality, estimated by ISOMAP, of the data can also be judged more easily by our method.