Capsule network is a novel architecture to encode the properties and spatial relationships of the feature in an image, which shows encouraging results on image classification. However, the original capsule network is not suitable for some classification tasks, where the target objects are complex internal representations. Hence, we propose a multi-scale capsule network that is more robust and efficient for feature representation in image classification. The proposed multi-scale capsule network consists of two stages. In the first stage, structural and semantic information are obtained by multi-scale feature extraction. In the second stage, the hierarchy of features is encoded to multi-dimensional primary capsules. Moreover, we propose an improved dropout to enhance the robustness of the capsule network. Experimental results show that our method has a competitive performance on FashionMNIST and CIFAR10 datasets.

In this paper, we present an approach to image enhancement with diffusion model in underwater scenes. Our method adapts conditional denoising diffusion probabilistic models to generate the corresponding enhanced images by using the underwater images and the Gaussian noise as the inputs. Additionally, in order to improve the efficiency of the reverse process in the diffusion model, we adopt two different ways. We firstly propose a lightweight transformer-based denoising network, which can effectively promote the time of network forward per iteration. On the other hand, we introduce a skip sampling strategy to reduce the number of iterations. Besides, based on the skip sampling strategy, we propose two different non-uniform sampling methods for the sequence of the time step, namely piecewise sampling and searching with the evolutionary algorithm. Both of them are effective and can further improve performance by using the same steps against the previous uniform sampling. In the end, we conduct a relative evaluation of the widely used underwater enhancement datasets between the recent state-of-the-art methods and the proposed approach. The experimental results prove that our approach can achieve both competitive performance and high efficiency. Our code is available at https://github.com/piggy2009/DM_underwater.

Recently, deep learning techniques have substantially boosted the performance of salient object detection in still images. However, the salient object detection in videos by using traditional handcrafted features or deep learning features is not fully investigated, probably due to the lack of sufficient manually labeled video data for saliency modeling, especially for the data-driven deep learning. This paper proposes a novel weakly supervised approach to salient object detection in a video, which can learn a robust saliency prediction model by using very limited manually labeled data and a large amount of weakly labeled data that could be easily generated in a supervised approach. Furthermore, we propose a spatiotemporal cascade neural network (SCNN) architecture for saliency modeling, in which two fully convolutional networks are cascaded to evaluate visual saliency from both spatial and temporal cues to lead the optimal video saliency prediction. The proposed approach is extensively evaluated on the widely used challenging datasets, and the experiments demonstrate that our proposed approach substantially outperforms the state-of-the-art salient object detection models.

Backlit image enhancement (BIE) aims to address image degradation caused by challenging lighting conditions. By enhancing the illumination of underexposed areas and restoring image details while avoiding overexposure, it achieves an overall harmonious luminance. In contrast to traditional BIE methods that apply global enhancements with limited effectiveness, we propose a controllable Mamba-based enhancement method, termed Control-Lit. Our method not only delivers effective backlit image enhancement but also allows users to interactively adjust the illumination of specific regions. Control-Lit achieves superior global enhancement performance by employing the Dark Channel Prior (DCP)-based Finite Scalar Quantization (DFSQ) module that provides a high-quality image prior. Additionally, the Dark Channel Prior Enhancement (DCPE) module is designed to guide the network in pixel-wise illumination adjustment at the feature level, thereby achieving enhancement of backlit regions. Furthermore, to address the loss of content and details in backlit regions, the Global-Local Vision State Space (GLVSS) module is incorporated to extract both global and local features for BIE. To enable customizable, controllable enhancement, we introduce an illumination control vector. By adjusting the coefficient map elements that are multiplied by this vector, users can achieve precise regional illumination adjustments. To further validate the generalization of different light enhancement methods, we contribute a synthetic backlit image dataset using a relighting generative model. Along with current widely used datasets, the experimental results demonstrate that our method achieves state-of-the-art performance on all datasets while enabling high-quality and controllable image illumination adjustment. The code is available at https://github.com/wuhj43/Control-Lit.

Currently, existing drone datasets mainly focus on collecting data in urban environments. However, there are numerous residential and farming areas located alongside the river in rural regions. If there is heavy rain and flooding, the river is likely to overflow, posing a threat to human lives and property. In this paper, we collect a novel drone-captured dataset, called DroneRiver, tailored for water management of pre-disaster scenarios and analysis of preliminary river leakage in rural areas. DroneRiver provides annotations for the objects on both sides of the river, such as people, vehicles, levee roads, farms, vegetation, etc. Additionally, to overcome the difficulty of collecting real-world river leakage scenes without environmental harm, based on the recent generative model, preliminary river leakage images can be generated in our datasets for pre-disaster prevention and alerts. Finally, our dataset annotates the original and generated aerial at the pixel level for semantic segmentation. We also conduct extensive experiments using state-of-the-art segmentation models and evaluate the quality of the generated aerial images. The results demonstrate the significance of the DroneRiver dataset for river leakage analysis.