Chang Niu

Embodied agents operating in human-populated environments need structured social perception: they must identify who interacts with whom, distinguish social groups from outliers, and recognize what each group is doing. Existing query-based methods infer group membership mainly from latent group tokens and activity semantics, leaving the underlying actor-actor structure implicit. We propose AGGD, an affinity-guided framework that makes this structure explicit. Its pairwise affinity branch estimates same-group relations from actor appearance and spatial cues, and connected component decomposition converts the resulting affinity graph into group instances and outliers. The learned structure also guides the query-based membership representation through an affinity-guided contrastive objective, linking discovered groups to group-level activity semantics. A LoRA-adapted visual foundation encoder supplies actor-centric features for both structural and semantic reasoning. Experiments on Café and Social-CAD show state-of-the-art performance in group detection and group activity prediction. The results indicate that explicit actor-actor affinity provides reliable structural guidance for social activity understanding in complex multi-group scenes.

The non‐independent and identically distributed (non‐IID) nature of data across different sites and the dynamic participation of client nodes represent two critical challenges faced by distributed industrial visual defect detection systems. While asynchronous federated learning (AFL) reduces training inefficiencies, its asynchronous update process makes the global model more vulnerable to data heterogeneity. This research proposes a contrastive clustering–based asynchronous federated learning (CC‐AFL) framework. The method integrates contrastive learning into the client clustering process, working simultaneously across instance‐level and cluster‐level spaces to identify hidden similarity patterns among participating clients. The server maintains update queues for each cluster and then applies staleness‐weighted aggregation based on the combined timestamp. Meanwhile, the framework uses client scheduling based on cluster queue lengths, giving priority to clusters with fewer updates to balance update frequencies across different clusters. Without requiring raw data sharing, the framework achieves improvements in both convergence speed and stability of AFL under changing scenarios. On the furniture board dataset, CC‐AFL achieves better performance with an average area under the receiver operating characteristic curve (I‐AUROC) of 74.38%, showing a 2.22% improvement over AFL‐DCS under different non‐IID settings. Experimental results show that CC‐AFL maintains stable convergence under different conditions, confirming the effectiveness and practical value of contrastive clustering and scheduling in AFL.

Automatic medical image segmentation is a fundamental component of computer-aided diagnosis. U-shaped networks (U-Nets) remain the most widely adopted architecture due to their suitability for the unique challenges of medical imaging. However, recent studies have shown that U-Nets fuse low-level visual features from the encoder with high-level semantic features from the decoder using direct skip connections (DSC), which are likely to degrade segmentation performance due to the semantic gap, thereby limiting their ability to meet high-precision clinical requirements. This paper revisits the semantic gap from a performance-oriented perspective and conceptualizes it as a learnable task. A key characteristic of this semantic gap is revealed through comprehensive quantification and visualization, demonstrating its significant negative impact on segmentation performance. Further analysis indicates that a contributing factor is the substantial channel noise present in low-level pixel features, which is transmitted to the decoder via DSC, thereby disrupting the modeling of high-level semantic representations. In response, this paper proposes a self-disambiguating skip connection (SDSC), which incorporates a self-guided filter leveraging spatial features for channel filtering, a multi-layer fusion Transformer to capture long-range contextual dependencies, and Jensen-Shannon divergence as a constraint to enhance learning. The proposed method, referred to as SDSC-UNet, is evaluated through extensive experiments on four challenging benchmarks. The results demonstrate that replacing DSC with our SDSC yields an improvement of 5.91% in mean Intersection over Union (mIoU), 4.58% in Dice coefficient, and 1.32 in Hausdorff Distance, achieving state-of-the-art performance and highlighting the effectiveness of SDSC.

Vision-based industrial inspection (VII) aims to locate defects quickly and accurately. Supervised learning under a close-set setting and industrial anomaly detection, as two common paradigms in VII, face different problems in practical applications. The former is that various and sufficient defects are difficult to obtain, while the latter is that specific defects cannot be located. To solve these problems, in this article, we focus on the few-shot semantic segmentation (FSS) method, which can locate unseen defects conditioned on a few annotations without retraining. Compared to common objects in natural images, the defects in VII are small. This brings two problems to current FSS methods: first, distortion of target semantics and second, many false positives for backgrounds. To alleviate these problems, we propose a small object few-shot segmentation (SOFS) model. The key idea for alleviating, first, is to avoid the resizing of the original image and correctly indicate the intensity of target semantics. SOFS achieves this idea via the nonresizing procedure and the prototype intensity downsampling of support annotations. To alleviate, second, we design an abnormal prior map in SOFS to guide the model in reducing false positives and propose a mixed normal dice loss to prevent the model from predicting false positives preferentially. SOFS can achieve FSS and few-shot anomaly detection determined by support masks. Diverse experiments substantiate the superior performance of SOFS.