With the development of foundation models, advanced research explores the potential of vision-language models (VLMs) for out-of-distribution (OOD) detection. In particular, methods that generate outliers for regularized prompt learning have shown promising results in few-shot settings. However, existing methods that rely solely on visual modalities struggle to synthesize outliers semantically analogous to in-distribution (ID) data, neglecting near OOD scenarios. Notably, recent large language models (LLMs) exhibit a deep real-world understanding, enabling the generation of near textual outliers. Inspired by this, we propose an OOD detection framework named TextAugmented Cues (TAC), which integrates expert knowledge from LLMs into the prompt learning of VLMs. Specifically, we first design LLMs query templates to generate outlier categories based on Visual Similarity. Then, LLMs are further leveraged to synthesize the semantic representations of ID and outlier categories based on Feature Distinctiveness. Subsequently, we incorporate visual-textual information of ID categories for prompt learning, regularized by textual outliers. Experimental results demonstrate that TAC significantly outperforms state-of-the-art (SOTA) VLMbased OOD detection methods in few-shot scenarios. The code is available at https://github.com/njustkmg/ICDM25-TAC.

Ship detection plays a critical role in intelligent maritime applications including port management, marine monitoring and so on. Most existing ship detectors are trained on high-quality conventional-sized ship images under normal lighting conditions. However,low-quality images with poor lighting conditions often exist, where the features are difficult to be distinguished. Additionally, small ships with fewer pixels exhibit minimal appearance information and weak contour characteristics in night scenes, which are harmful to the multi-scale feature fusion. To address the above challenges, we propose an effective multi-scale feature fusion network for small ship detection in night scenes named MFF-YOLO. Specifically, we first design a night-friendly enhanced channel attention module, to better represent channel-dimensional features of small ships. In addition, we construct a multi-scale feature fusion architecture based on space and channel, to obtain richer semantic information of small ships in poor lighting conditions and further enhance the feature distinguishability. Finally, a series of experiments are implemented and corresponding results demonstrate the effectiveness and feasibility of our proposed method.

Videos such as movies or TV episodes usually need to divide the long storyline into cohesive units, i.e., scenes, to facilitate the understanding of video semantics. The key challenge lies in finding the boundaries of scenes by comprehensively considering the complex temporal structure and semantic information. To this end, we introduce a novel Context-Aware Transformer (CAT) with a self-supervised learning framework to learn high-quality shot representations, for generating well-bounded scenes. More specifically, we design the CAT with local-global self-attentions, which can effectively consider both the long-term and short-term context to improve the shot encoding. For training the CAT, we adopt the self-supervised learning schema. Firstly, we leverage shot-to-scene level pretext tasks to facilitate the pre-training with pseudo boundary, which guides CAT to learn the discriminative shot representations that maximize intra-scene similarity and inter-scene discrimination in an unsupervised manner. Then, we transfer contextual representations for fine-tuning the CAT with supervised data, which encourages CAT to accurately detect the boundary for scene segmentation. As a result, CAT is able to learn the context-aware shot representations and provides global guidance for scene segmentation. Our empirical analyses show that CAT can achieve state-of-the-art performance when conducting the scene segmentation task on the MovieNet dataset, e.g., offering 2.15 improvements on AP.

Existing semi-supervised learning (SSL) methods assume that labeled and unlabeled data share the same class space. However, in real-world applications, unlabeled data always contain classes not present in the labeled set, which may cause classification performance degradation of known classes. Therefore, open-world SSL approaches are researched to handle the presence of multiple unknown classes in the unlabeled data, which aims to accurately classify known classes while fine-grained distinguishing different unknown classes. To address this challenge, in this paper, we propose an open-world SSL method for Self-learning Open-world Classes (SSOC), which can explicitly self-learn multiple unknown classes. Specifically, SSOC first defines class center tokens for both known and unknown classes and autonomously learns token representations according to all samples with the cross-attention mechanism. To effectively discover novel classes, SSOC further designs a pairwise similarity loss in addition to the entropy loss, which can wisely exploit the information available in unlabeled data from instances’ predictions and relationships. Extensive experiments demonstrate that SSOC outperforms the state-of-the-art baselines on multiple popular classification benchmarks. Specifically, on the ImageNet-100 dataset with a novel ratio of $90 \%$, SSOC achieves a remarkable $16 \%$ improvement.

Electroluminescence imaging becomes a very useful technique to automatically detect defects for solar cells since it can provide high resolution electroluminescence images. However, few methods explicitly consider the visual characteristics of the defects and the noises in solar cells. In this article, a global pairwise similarity and concatenated saliency guided neural network is proposed by fully considering the observed visual characteristics in electroluminescence solar cell images. The proposed network exploits a global pairwise similarity module and a concatenated saliency module to refine the features extracted by the convolutional neural network. The global pairwise similarity module aims to refine the features of an image pixel by modeling long-range dependencies. The concatenated saliency module is exploited to suppress the background and decouple different salient regions to better represent the features of an image. Extensive experiments based on five different baselines, i.e., VGG16, ResNet56, ResNet50, DenseNet40, and GoogleNet, prove that the proposed method significantly outperforms the baseline models and show that both the global similarity module and the concatenated saliency module can help detect defective solar cells in electroluminescence images.

Multiview learning has received substantial attention over the past decade due to its powerful capacity in integrating various types of information. Conventional unsupervised multiview dimension reduction (UMDR) methods are usually conducted in an offline manner and may fail in many real-world applications, where data arrive sequentially and the data distribution changes periodically. Moreover, satisfying the requirements of high memory consumption and expensive retraining of the time cost in large-scale scenarios are difficult. To remedy these drawbacks, we propose an online UMDR (OUMDR) framework. OUMDR aims to seek a low-dimensional and informative consensus representation for streaming multiview data. View-specific weights are also learned in this article to reflect the contributions of different views to the final consensus presentation. A specific model called OUMDR-E is developed by introducing the exclusive group LASSO (EG-LASSO) to explore the intraview and interview correlations. Then, we develop an efficient iterative algorithm with limited memory and time cost requirements for optimization, where the convergence of each update is theoretically guaranteed. We evaluate the proposed approach in video-based expression recognition applications. The experimental results demonstrate the superiority of our approach in terms of both effectiveness and efficiency.

For the widely used multilayer perceptrons (MLPs), the existed singularities in the parameter space have seriously affected the learning dynamics of MLPs, which cause several singular learning behaviors. Since the Fisher information matrix (FIM) plays a significant role in analyzing the singular learning dyanmics of MLPs, it is very worthy to obtain the analytical form of FIM to do further investigation. In this paper, by choosing the bipolar error function as the activation function, the analytical form of FIM are obtained, where the validity of the obtained results are verified by taking three experiments.

The multilayer perceptrons (MLPs) are widely used in many fields, however, singularities in the parameter space may seriously influence the learning dynamics of MLPs and cause strange learning behaviors. Given that the singularities are the subspaces of the parameter space where the Fisher information matrix (FIM) degenerates, the FIM plays a key role in the study of the singular learning dynamics of the MLPs. In this paper, we obtain the analytical form of the FIM for unipolar activation function-based MLPs where the input subjects to the Gaussian distribution with general covariance matrix and the unipolar error function is chosen as the activation function. Then three simulation experiments are taken to verify the validity of the obtained results.

The existence of singularities often affects the learning dynamics in feedforward neural networks. In this paper, based on theoretical analysis results, we numerically analyze the learning dynamics of radial basis function (RBF) networks near singularities to understand to what extent singularities influence the learning dynamics. First, we show the explicit expression of the Fisher information matrix for RBF networks. Second, we demonstrate through numerical simulations that the singularities have a significant impact on the learning dynamics of RBF networks. Our results show that overlap singularities mainly have influence on the low dimensional RBF networks and elimination singularities have a more significant impact to the learning processes than overlap singularities in both low and high dimensional RBF networks, whereas the plateau phenomena are mainly caused by the elimination singularities. The results can also be the foundation to investigate the singular learning dynamics in deep feedforward neural networks.

Radial basis function (RBF) networks are one of the most widely used models for function approximation and classification. There are many strange behaviors in the learning process of RBF networks, such as slow learning speed and the existence of the plateaus. The natural gradient learning method can overcome these disadvantages effectively. It can accelerate the dynamics of learning and avoid plateaus. In this letter, we assume that the probability density function (pdf) of the input and the activation function are gaussian. First, we introduce natural gradient learning to the RBF networks and give the explicit forms of the Fisher information matrix and its inverse. Second, since it is difficult to calculate the Fisher information matrix and its inverse when the numbers of the hidden units and the dimensions of the input are large, we introduce the adaptive method to the natural gradient learning algorithms. Finally, we give an explicit form of the adaptive natural gradient learning algorithm and compare it to the conventional gradient descent method. Simulations show that the proposed adaptive natural gradient method, which can avoid the plateaus effectively, has a good performance when RBF networks are used for nonlinear functions approximation.