Logit Knowledge Distillation has gained substantial research interest in recent years due to its simplicity and lack of requirement for intermediate feature alignment; however, it suffers from limited interpretability in its decision-making process. To address this, we propose implicit Clustering Distillation (iCD): a simple and effective method that mines and transfers interpretable structural knowledge from logits, without requiring ground-truth labels or feature-space alignment. iCD leverages Gram matrices over decoupled local logit representations to enable student models to learn latent semantic structural patterns. Extensive experiments on benchmark datasets demonstrate the effectiveness of iCD across diverse teacher-student architectures, with particularly strong performance in fine-grained classification tasks---achieving a peak improvement of +5.08% over the baseline.

Accurate detection of surface defects on wind turbine blades (WTB) is essential to ensure the safety of wind turbines and optimize power generation efficiency. Current detection methods face two main challenges: (1) imbalanced data distribution, which hampers accurate detection of rare but critical defect types, and (2) varying detection difficulty across categories, where small targets or defects with unclear boundaries complicate reliable results for difficult-to-detect classes. To address these issues, we propose an improved YOLO11-based detection model featuring three key innovations: (1) the ADown dual-path downsampling module from YOLOv9, which preserves important fine-grained features during extraction, (2) the EdgeAttention module to improve detection of small defects and edge-distributed flaws in complex backgrounds; and (3) the DSM (Dual Selection Mechanism), which dynamically ranks and adaptively weights harder defect categories for better detection. In addition, we develop custom data augmentation and hyperparameter optimization strategies adapted to this updated model. Experiments on the WTB dataset show that our proposed model outperforms the latest methods, achieving [email protected] of 86.9%. Furthermore, it demonstrates an approximately 10% improvement in the detection of challenging and rare defect categories. These results underscore our model’s potential to enhance wind farm maintenance efficiency while reducing safety risks.

Anomaly detection plays a crucial role in quality control within the manufacturing industry. Traditional computer vision approaches typically adopt reconstruction-based strategies, where the distribution of normal features is modeled to suppress the reconstruction of anomalous regions. Although these methods generally require fewer data, they often struggle to simultaneously improve reconstruction quality and detection performance. Experimental results indicate that high-level semantic context features exhibit strong capabilities in identifying anomalies, while low-level features contribute to the representation of global characteristics. Based on this, the paper uses discrete wavelet transform (DWT) to decompose images into low- and high-frequency components, extracting both global and local features. The input image is encoded in parallel using convolutional encoders and fused with the base features extracted through DWT. To further enhance detection performance, we propose a customized feature fusion module inspired by Feature Pyramid Networks (FPN), which integrates spatial and channel attention mechanisms to strengthen the model's ability to capture inter-feature relationships. Finally, extensive comparative and ablation experiments conducted on public benchmark datasets demonstrate the effectiveness of the proposed method.

Conventional Neural Machine Translation (NMT) relies on previous tokens and the hidden state of the target for the inference of the target tokens in the decoding phase, and this left-to-right decoding approach loses the context of the target sequence from right-to-left. In addition, the vanilla attention mechanism lacks interactivity in the bilingual training phase, where the computation of the attention weights is independent at each step, which leads the decoder to disregard whether or not the current token has already been translated. In this paper, we proposed a novel interactive synchronized bi-directional inference method that uses past and future contexts to synchronously predict target sequences and incorporates Neural Turing Machine (NTM) ideas to detect historical attentional information, which relies on a read − write mechanism to update the source hidden state. We evaluate the proposed model in the WMT14 German-English translation task and the LDC Chinese-English translation task, and the experimental results show that our method improves 2.18 and 4.07 BLEU scores over the Transformer, respectively, which fully demonstrates the effectiveness of the proposed method.