Accurate assessment of food nutrition is essential for promoting healthy eating habits. While recent deep learning approaches have enhanced vision-based nutritional estimation through RGB-D multi-modal fusion, they often overlook fine-grained surface components (e.g., oil and sugar) that significantly influence nutritional values. Some recent approaches have improved accuracy by incorporating ingredient data, but their reliance on such input during inference limits practical applicability, as ingredient details are often unavailable in real-world settings. To address this limitation, we propose DSDGF-Nutri, a novel Decoupled Self-Distillation network with Gating Fusion for food Nutri tional assessment. Our method leverages ingredient knowledge during training but relies solely on RGB-D inputs at inference. Specifically, DSDGF-Nutri introduces: (1) a self-distillation mechanism with gating fusion that transfers ingredient-aware features to the RGB-D network, enabling robust prediction without test-time ingredient input, and (2) a multi-task decoupling architecture with task-specific decoders to minimize cross-task interference. Extensive evaluations on two benchmark datasets demonstrate DSDGF-Nutri outperforms existing methods, achieving state-of-the-art results. This work establishes a new paradigm of multimodal fusion in nutritional assessment by unifying scientific measurements with scalable computer vision applications.

ABSTRACT Deep neural networks deployed on UAVs have made significant progress in data acquisition in recent years. However, traditional algorithms and deep learning models still face challenges in small and unevenly distributed object detection tasks. To address this problem, we propose the MCD‐YOLOv10n model by introducing the MEMAttention module, which combines EMAttention with multiscale convolution, uses Softmax and AdaptiveAvgPool2d to adaptively compute feature weights, dynamically adjusts the region of interest, and captures cross‐scale features. In addition, the C2f_MEMAttention and C2f_DSConv modules are formed by the fusion of C2f with MEMAttention and DSConv, which enhances the model's ability of extracting and adapting to irregular target features. Experiments on three datasets, VisDrone‐DET2019, Exdark and DOTA‐v1.5, show that the evaluation metric mAP50 achieves the best detection accuracy of 32.9%, 52.9% and 68.2% when the number of holdout parameters is at the minimum value of 2.24M. Moreover, the mAP50‐95 metrics (19.5% for VisDrone‐DET2019 and 45.0% for DOTA‐v1.5) are 1.1 and 1.2 percentage points ahead of the second place, respectively. In terms of Recall, the VisDrone‐DET2019 and DOTA‐v1.5 datasets improved by 1.0% and 0.7% over the baseline model. These results validate that MCD‐YOLOv10n has strong adaptability and generalization ability for small object detection in complex scenes.

Extracting signal photons from noisy raw data is one of the critical processes for the new generation of spaceborne photon-counting laser altimeter. Affected by vast noise photon-counting events, the extraction of weak signal events still faces challenges in complex scenarios with low signal-to-noise ratio (SNR). Aiming to improve the extraction ability of signal photon events in these scenarios, a multiscale fusion signal extraction method was proposed, characterized by combining global spatial correlation constraint with optimized local spatial correlation constraint. The local constraint is implemented based on a density-based spatial clustering of applications with noise (DBSCAN) clustering method with adaptive parameter estimation, which is used to extract possible signal photons. A subsequent global constraint based on the spatial correlation of the terrain profiles is designed to remove the pseudo-signal photons clustered in the local constraints’ step. The global constraint is implemented based on a cost function, which is used to quantify different candidate paths. Our method was verified based on the actual Ice, Cloud, and land Elevation satellite-(ICESat2) data containing vegetation, mountains, and residential areas. The experimental results show that compared with the ICESat-2 extraction method, our method can significantly improve the precision and recall rate of signal photon events from the low SNR photon-counting data.