Recently, we have witnessed substantial success using the deep neural network in many tasks. While there still exists concerns about the explainability of decision-making, it is beneficial for users to discern the defects in the deployed deep models. Existing explainable models either provide the image-level visualization of attention weights or generate textual descriptions as post-hoc justifications. Different from existing models, in this paper, we propose a new interpretation method that explains the image similarity models by salience maps and attribute words. Our interpretation model contains visual salience maps generation and the counterfactual explanation generation. The former has two branches: global identity relevant region discovery and multi-attribute semantic region discovery. Branch one aims to capture the visual evidence supporting the similarity score, which is achieved by computing counterfactual feature maps. Branch two aims to discover semantic regions supporting different attributes, which helps to understand which attributes in an image might change the similarity score. Then, by fusing visual evidence from two branches, we can obtain the salience maps indicating important response evidence. The latter will generate the attribute words that best explain the similarity using the proposed erasing model. The effectiveness of our model is evaluated on the classical face verification task. Experiments conducted on two benchmarks VGG-Face2 and Celeb-A demonstrate that our model can provide convincing interpretable explanations for the similarity. Moreover, our algorithm can be applied to evidential learning cases, e.g. finding the most characteristic attributes in a set of face images and we verify its effectiveness on the VGGFace2 dataset.

The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples. The key challenge is constructing a generalized feature space for novel categories with limited data, leveraging the base category space to adapt the detection model. Most fine-tuning methods address this by pre-training on base categories and fine-tuning on novel ones. However, limited novel samples lead to two issues: (1) the features of the novel category are easily implicitly represented by the features of the base category, leading to inseparable classifier boundaries, (2) novel categories with fewer data are not enough to fully represent the distribution, where the model fine-tuning is prone to overfitting. To address these issues, we propose a generalized feature learning method for FSOD by leveraging side information. Specifically, we first construct a knowledge matrix from embedded side information to model semantic relations between base and novel categories. Then, to strengthen the discrimination between semantically similar categories, we further develop contextual semantic supervised contrastive learning which embeds side information. To mitigate overfitting from limited samples, we introduce a side-information guided region-aware masking module that improves sample diversity by removing biased information through counterfactual explanations. Extensive experiments using ResNet and ViT backbones on PASCAL VOC, MS COCO, LVIS V1, FSOD-1K, and FSVOD-500 benchmarks demonstrate that our model outperforms the previous state-of-the-art methods, significantly improving the ability of FSOD in most shots/splits.

The increasing consumption of ducks and chickens in China demands characterizing carcasses of domestic birds efficiently. Most existing methods, however, were developed for characterizing carcasses of pigs or cattle. Here, we developed a noncontact and automated weighing method for duck carcasses hanging on a production line. A 2D camera with its facilitating parts recorded the moving duck carcasses on the production line. To estimate the weight of carcasses, the images in the acquired dataset were modeled by a convolution neuron network (CNN). This model was trained and evaluated using 10-fold cross-validation. The model estimated the weight of duck carcasses precisely with a mean abstract deviation ( MAD ) of 58.8 grams and a mean relative error ( MRE ) of 2.15% in the testing dataset. Compared with 2 widely used methods, pixel area linear regression and the artificial neural network (ANN) model, our model decreases the estimation error MAD by 64.7 grams (52.4%) and 48.2 grams (45.0%). We release the dataset and code at https://github.com/RuoyuChen10/Image_weighing.

Multi-modal image fusion (MMIF) aims to integrate complementary information from heterogeneous sensor modalities. However, substantial cross-modality discrepancies hinder joint scene representation and lead to semantic degradation in the fused output. To address this limitation, we propose C²MFuse, a novel framework designed to preserve content while ensuring cross-modality consistency. To the best of our knowledge, this is the first MMIF approach to explicitly disentangle style and content representations across modalities for image fusion. C²MFuse introduces a content-preserving style normalization mechanism that suppresses modality-specific variations while maintaining the underlying scene structure. The normalized features are then progressively aggregated to enhance fine-grained details and improve content completeness. In light of the lack of ground truth and the inherent ambiguity of the fused distribution, we further align the fused representation with a well-defined source modality, thereby enhancing semantic consistency and reducing distributional uncertainty. Additionally, we introduce an adaptive consistency loss with learnable transformation, which provides dynamic, modality-aware supervision by enforcing global consistency across heterogeneous inputs. Extensive experiments on five datasets across three representative MMIF tasks demonstrate that C²MFuse achieves efficient and high-quality fusion, surpasses existing methods, and generalizes effectively to downstream visual applications.

Intelligent sensing technologies are transforming sports training by enabling precise motion analysis, critical for skill development and performance optimization. This study introduces a badminton racket handle embedded with a lightweight, multinode MEMS-based sensing system designed for real-time motion recognition. To capture distributed grip forces, swing trajectories, and impact mechanics at the player-equipment interface, the system employs an ergonomic design ensuring natural gameplay. A hybrid feature extraction approach, integrating time- and frequency-domain features with a 1-D-convolutional neural network (CNN), achieves a classification accuracy of 97.89% across ten badminton actions. To enhance interpretability and provide actionable insights, explainable AI using SMDL-attribution identifies key motion features, revealing biomechanical inefficiencies in grip strength, swing consistency, and wrist motion. Seamlessly integrated with virtual reality (VR) platforms, the system delivers immersive, real-time feedback, transforming training into an interactive and data-driven experience. By combining advanced sensing, machine learning, and explainable AI, this system establishes a new benchmark for intelligent sports monitoring, with broad applications in sports training, rehabilitation, and human-computer interaction.