Compared with hardware upgrading, pansharpening is a low-cost way to acquire high-quality images, which usually combines multispectral images (MS) in low spatial resolution with panchromatic images (PAN) in high spatial resolution. This paper proposes a pixel-dependent spatial-detail injection network (PDSDNet). Based on a dynamic filter network, PDSDNet constructs nonlinear mapping of the simulated panchromatic band from low-resolution multispectral bands through filtering convolution regression. PDSDNet reduces the possibility of spectral distortion and enriches spatial details by improving the similarity between the simulated panchromatic band and the real panchromatic band. Moreover, PDSDNet assumes that if an ideal multispectral image that has the same resolution with the panchromatic image exists, each band of it should have the same spatial details as in the panchromatic image. Thus, the details we fill into each multispectral band are the same and they can be extracted effectively in one pass. Experimental results demonstrate that PDSDNet can generate high-quality fusion images with multispectral images and panchromatic images. Compared with BDSD, MTF-GLP-HPM-PP, and PanNet, which are widely applied on IKONOS, QuickBird, and WorldView-3 datasets, pansharpened images of the proposed method have rich spatial details and present superior visual effects without noticeable spectral and spatial distortion.

In the past few years, feature fusion-based violence detection has made remarkable progress. However, existing detection methods primarily focus on temporal feature analysis, which may result in an insufficient representation of the subtle variations inherent in violent behaviors, ultimately compromising detection performance. To overcome this limitation, this study introduces a Wavelet-Based Time–Frequency Feature Fusion (WTFF) method. Specifically, the Wavelet-Dilated Separable Convolution Module (WDCM) and the Time–Frequency Feature Fusion (TFFF) Network are designed. Firstly, the input video data is utilized by the WDCM to extract and process frequency-domain features, enabling the model to capture fine-grained behavioral details often overlooked in temporal analysis. Secondly, the TFFF fuses the temporal and frequency-domain features, thereby improving the model’s ability to discriminate violent events. Ultimately, the effectiveness and superiority of the proposed approach are demonstrated by experimental results on UCF-Crime, XD-Violence, and ShanghaiTech datasets, achieving 85.87% (AUC), 84.77% (AP), and 97.91% (AUC), respectively.

Targeted fine-tuning of lightweight convolutional neural networks (CNNs) is a core approach to enabling edge devices to adapt to personalized scenarios with limited resources. However, most existing methods suffer from both insufficient adaptability and poor robustness in edge scenarios, due to their mismatch with lightweight CNN architectures and a lack of specific optimization for noisy environments. To this end, this paper proposes an efficient and robust fine-tuning method for lightweight CNNs, which we call PoinT. PoinT introduces a fine-tuning branch that is consistent with the backbone’s structure and informed by lightweight CNNs. In the fine-tuning branch, PoinT designates a set of seed filters, and the remaining filters are generated from the seed filters and a nonlinear transformation function (NTF) with configured untrainable parameters. NTF with fixed hyperparameters prevents model parameter updates from being entirely dependent on training data, regularizes the model, and thus improves its robustness. In addition, the number of seed filters is dynamically controllable, enabling adaptation to changing resource availability on IoT devices. Experimental results on the CIFAR-10/100, CIFAR-10-C/-100-C, and Icons-50 datasets, when applied to architectures such as MobileNetV2, ShuffleNetV2, EfficientNet, and GhostNet, demonstrate that the model is more robust than training from scratch or fully fine-tuning. Specifically, on the CIFAR-10-C dataset, PoinT based on ShuffleNetV2 achieves an accuracy about 7.8% higher than that of fully fine-tuned models, while reducing the number of trainable parameters by more than 65%.

Deploying lightweight convolutional neural networks (CNNs) to provide vision services on resource-constrained Internet of Things (IoT) devices has become the mainstream approach to addressing computing and energy consumption constraints. However, these IoT devices often operate in complex outdoor environments (e.g., fog, rain, and snow), and the quality of the data they collect is easily degraded, causing standard lightweight CNNs to experience a significant performance drop under such corrupted data. To this end, this paper proposes a Generative Nonlinear Transformation Filter (GNTF) method to improve the generalization performance of lightweight CNNs on corrupted data. The core of the GNTF is that only a portion of the filters are used as learnable parameters (named seed filters), while the remaining filters are generated by applying the nonlinear transformation to the seed filters, which is randomly initialized and fixed during training. This design makes the model parameters less dependent on the training data distribution, thereby regularizing the model, mitigating overfitting, and enhancing its robustness to data degradation. The GNTF further analyzes the structural characteristics of lightweight CNNs, showing that significant performance improvements can be achieved simply by replacing the depthwise convolutional modules. Furthermore, this paper examines the properties of various nonlinear transformation functions and finds that model robustness can be improved by applying simple translations. To verify the effectiveness of the GNTF, we conducted extensive experiments on the CIFAR-10/-100, CIFAR-10-C/-100-C, and ICONS-50 datasets, using the MobileNetV2, ShuffleNetV2, EfficientNet, and GhostNet models. The results show that the proposed GNTF can improve the model’s accuracy on corrupted data while reducing the number of trainable parameters in most cases. For example, on the CIFAR-10-C dataset, ShuffleNetV2 with the GNTF improves accuracy by about 3.3% over the original model while slightly reducing the number of trainable parameters.