Compared with conventional targets, small objects often face challenges such as smaller size, lower resolution, weaker contrast, and more background interference, making their detection more difficult. To address this issue, this paper proposes an improved small object detection method based on the YOLO11 model—PC-YOLO11s. The core innovation of PC-YOLO11s lies in the optimization of the detection network structure, which includes the following aspects: Firstly, PC-YOLO11s has adjusted the hierarchical structure of the detection network and added a P2 layer specifically for small object detection. By extracting the feature information of small objects in the high-resolution stage of the image, the P2 layer helps the network better capture small objects. At the same time, in order to reduce unnecessary calculations and lower the complexity of the model, we removed the P5 layer. In addition, we have introduced the coordinate spatial attention mechanism, which can help the network more accurately obtain the spatial and positional features required for small targets, thereby further improving detection accuracy. In the VisDrone2019 datasets, experimental results show that PC-YOLO11s outperforms other existing YOLO-series models in overall performance. Compared with the baseline YOLO11s model, PC-YOLO11s mAP@0.5 increased from 39.5% to 43.8%, mAP@0.5:0.95 increased from 23.6% to 26.3%, and the parameter count decreased from 9.416M to 7.103M. Not only that, we also applied PC-YOLO11s to tea bud datasets, and experiments showed that its performance is superior to other YOLO-series models. Experiments have shown that PC-YOLO11s exhibits excellent performance in small object detection tasks, with strong accuracy improvement and good generalization ability, which can meet the needs of small object detection in practical applications.

Existing multi-view graph learning methods often rely on consistent information for similar nodes within and across views, however they may lack adaptability when facing diversity challenges from noise, varied views, and complex data distributions. These challenges can be mainly categorized into: 1) View-specific diversity within intra-view from noise and incomplete information; 2) Cross-view diversity within inter-view caused by various latent semantics; 3) Cross-group diversity within inter-group due to data distribution differences. To this end, we propose a universal multi-view consensus graph learning framework that considers both original and generative graphs to balance consistency and diversity. Specifically, the proposed framework can be divided into the following four modules. i) Multi-channel graph module to extract principal node information, ensuring view-specific and cross-view consistency while mitigating view-specific and cross-view diversity within original graphs; ii) Generative module to produce cleaner and more realistic graphs, enriching graph structure while maintaining view-specific consistency and suppressing view-specific diversity; iii) Contrastive module to collaborate on generative semantics to facilitate cross-view consistency and reducing cross-view diversity within generative graphs; iv) Consensus graph module to consolidate learning a consensual graph, pursuing cross-group consistency and cross-group diversity. Extensive experimental results on real-world datasets demonstrate its effectiveness and superiority.

Existing representation learning approaches lie predominantly in designing models empirically without rigorous mathematical guidelines, neglecting interpretation in terms of modeling. In this work, we propose an optimization-derived representation learning network that embraces both interpretation and extensibility. To ensure interpretability at the design level, we adopt a transparent approach in customizing the representation learning network from an optimization perspective. This involves modularly stitching together components to meet specific requirements, enhancing flexibility and generality. Then, we convert the iterative solution of the convex optimization objective into the corresponding feed-forward network layers by embedding learnable modules. These above optimization-derived layers are seamlessly integrated into a deep neural network architecture, allowing for training in an end-to-end fashion. Furthermore, extra view-wise weights are introduced for multi-view learning to discriminate the contributions of representations from different views. The proposed method outperforms several advanced approaches on semi-supervised classification tasks, demonstrating its feasibility and effectiveness.