Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge. Thus it has triggered enormous research activities in machine learning and pattern recognition. One of the most important challenge of deep learning is to figure out relations between a feature and the depth of deep neural networks (deep nets for short) to reflect the necessity of depth. Our purpose is to quantify this feature-depth correspondence in feature extraction and generalization. We present the adaptivity of features to depths and vice-verse via showing a depth-parameter trade-off in extracting both single feature and composite features. Based on these results, we prove that implementing the classical empirical risk minimization on deep nets can achieve the optimal generalization performance for numerous learning tasks. Our theoretical results are verified by a series of numerical experiments including toy simulations and a real application of earthquake seismic intensity prediction.

Underwater object detection using side-scan sonar (SSS) remains a significant challenge in marine exploration, especially for small objects. Conventional methods for small object detection face various obstacles, such as difficulties in feature extraction and the considerable impact of noise on detection accuracy. To address these issues, this study proposes an improved YOLOv11 network named YOLOv11-SDC. Specifically, a new Sparse Feature (SF) module is proposed, replacing the Spatial Pyramid Pooling Fast (SPPF) module from the original YOLOv11 architecture to enhance object feature selection. Furthermore, the proposed YOLOv11-SDC integrates a Dilated Reparam Block (DRB) with a C3k2 module to broaden the model’s receptive field. A Content-Guided Attention Fusion (CGAF) module is also incorporated prior to the detection module to assign appropriate weights to various feature maps, thereby emphasizing the relevant object information. Experimental results clearly demonstrate the superiority of YOLOv11-SDC over several iterations of YOLO versions in detection performance. The proposed method was validated through extensive real-world experiments, yielding a precision of 0.934, recall of 0.698, mAP@0.5 of 0.825, and mAP@0.5:0.95 of 0.598. In conclusion, the improved YOLOv11-SDC offers a promising solution for detecting small objects in SSS images, showing substantial potential for marine applications.

Palm vein recognition is a high-security biometric. Outside the NIR capture box and contactless palm vein recognition are more popular but challenging. The users feel comfortable outside the NIR capture box but face more optical blurring brought by visible light. Contactless capture gestures solve the hygienic problem but face the image rotation, position translation, and scale transformation which makes classification difficult especially in large-scale databases. To address these problems, we develop a wavelet denoising ResNet, which consists of two models: the wavelet denoising (WD) model and the squeeze-and-excitation ResNet18 (SER) model. The WD model focuses on removing noise from skin scattering and optical blurring from palm vein images. The WD model enhances the low-frequency feature into a deep learning feature by residual learning technology. This strategy increases the weight of an effective handcrafted feature in the deep learning network. The SER model overcomes rotation, position translation, and scale transformation by selectively emphasizing classification features and weakening less useful features. To train and verify the network, an inside box palm vein image database and an outside box palm vein image database are set up. The Tongji contactless palm vein image database was also employed in the experiments. The validity and superiority of our network are verified in a series of experiments.

Underwater object detection is an important task in marine exploration. The existing autonomous underwater vehicle (AUV) designs typically lack an integrated object detection module and are constrained by communication limitations in underwater environments. This results in a situation where AUV, when tasked with object detection missions, require real-time transmission of underwater sensing data to shore-based stations but are unable to do so. Consequently, the task is divided into two discontinuous phases: AUV acquisition of underwater data and shore-based object detection, leading to limited autonomy and intelligence for the AUV. In this paper, we propose a novel autonomous online underwater object detection system for AUV based on side-scan sonar (SSS). This system encompasses both hardware and software components and enables AUV to perform simultaneous data acquisition and object detection for underwater objects, thereby providing guidance for coherent AUV underwater operations. Firstly, this paper outlines the hardware design and layout of a portable integrated AUV for reconnaissance and strike missions, achieving online object detection through the integration of an acoustic processing computer. Subsequently, a modular design for the software architecture and a multi-threaded parallel design for the software workflow are developed, along with the integration of the YOLOv7 intelligent detection model, addressing three key technological challenges: real-time data processing, autonomous object detection, and intelligent online detection. Finally, lake experiments show that the system can meet the autonomy and real-time requirements of predefined object detection on AUV, and the average positioning error is better than 5 m, which verifies the feasibility and effectiveness of the system. This provides a new solution for underwater object detection in AUV.

Image clustering is a complex procedure, which is significantly affected by the choice of image representation. Most of the existing image clustering methods treat representation learning and clustering separately, which usually bring two problems. On the one hand, image representations are difficult to select and the learned representations are not suitable for clustering. On the other hand, they inevitably involve some clustering step, which may bring some error and hurt the clustering results. To tackle these problems, we present a new clustering method that efficiently builds an image representation and precisely discovers cluster assignments. For this purpose, the image clustering task is regarded as a binary pairwise classification problem with local structure preservation. Specifically, we propose here such an approach for image clustering based on a fully convolutional autoencoder and deep adaptive clustering (DAC). To extract the essential representation and maintain the local structure, a fully convolutional autoencoder is applied. To manipulate feature to clustering space and obtain a suitable image representation, the DAC algorithm participates in the training of autoencoder. Our method can learn an image representation that is suitable for clustering and discover the precise clustering label for each image. A series of real-world image clustering experiments verify the effectiveness of the proposed algorithm.