Adopting Model-Based Development (MBD) in automotive software becomes necessary because it provides a rigorous development process. As the increase in the number of software components (SWCs) and their interactions, modifications to one part of the software might impact other parts due to the high coupling of SWCs. Developing an automated software refactoring technique to implement high cohesion and low coupling of software is necessary. Software refactoring usually contains code refactoring and architecture refactoring. Code refactoring only modifies the code inside the SWCs without changing its original functionality and external behavior, whereas current architecture refactoring does not consider the interaction weight (strength) between SWCs.In this study, we propose a weighted community division algorithm called Weighted-Girvan-Newman (W-GN) for software architecture refactoring. W-GN algorithm refactors the architecture by dividing SWCs into modules based on the interaction weights of SWCs. We further develop an automated architecture refactoring tool called AutoToolMD. This tool assists engineers in improving development efficiency and ensures the architecture aligns with the requirements of high cohesion and low coupling. Evaluations show that W-GN indicates more suitable modularity values than the traditional Girvan-Newman (GN) algorithm because the former can better reflect the real architecture with interaction weights. We apply AutoToolMD to automatically refactor architecture in automotive industry practice. Case study with the Zone_B PwrSplyMngt and Zone L_Lock modules in the Honda zone control software shows that AutoToolMD effectively refactors architecture with a significant improvement in testing efficiency and readability.

Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state and dynamically adjust the distilled solution space using contrastive learning. Additionally, we also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models. Note that the proposed DCKD is a structure-agnostic distillation framework, which can adapt to different backbones and can be combined with methods that optimize upper-bound constraints to further enhance model performance. Extensive experiments demonstrate that DCKD significantly outperforms the state-of-the-art KD methods across various image restoration tasks and backbones.

Weakly supervised semantic segmentation (WSSS) has garnered considerable attention due to its effective reduction of annotation costs. Most approaches utilize Class Activation Maps (CAM) to produce pseudo-labels, thereby localizing target regions using only image-level annotations. However, the prevalent methods relying on vision transformers (ViT) encounter an "over-expansion" issue, i.e., CAM incorrectly expands high activation value from the target object to the background regions, as it is difficult to learn pixel-level local intrinsic inductive bias in ViT from weak supervisions. To solve this problem, we propose a Progressive Confidence Region Expansion (PCRE) framework for WSSS, it gradually learns a faithful mask over the target region and utilizes this mask to correct the confusion in CAM. PCRE has two key components: Confidence Region Mask Expansion (CRME) and Class-Prototype Enhancement (CPE). CRME progressively expands the mask in the small region with the highest confidence, eventually encompassing the entire target, thereby avoiding unintended coverage of background areas. CPE aims to enhance mask generation in CRME by leveraging the similarity between the learned, dataset-level class prototypes and patch features as supervision to optimize the mask output from CRME. Extensive experiments demonstrate that our method outperforms the existing single-stage and multi-stage approaches on the PASCAL VOC and MS COCO benchmark. Our code is available at https://github.com/xxf011/WSSS-PCRE.

Open-vocabulary object detection seeks to recognize objects from arbitrary language inputs, extending detection beyond fixed training categories. While recent methods have made progress in detecting unseen categories, they typically require a set of predefined categories during the inference stage, hindering practical deployment in open-world scenarios. To overcome this crucial limitation, we propose UniPerception , a novel universal perception framework based on open-vocabulary object detection. It not only excels at open-vocabulary object detection but is also capable of generating labels for target objects in the absence of predefined vocabularies, and can be adapted to a broad range of vision-language tasks simply by modifying the language instructions. UniPerception seamlessly integrates three key innovations: 1) a robust visual detector trained on diverse data sources to capture rich and generalizable visual representations; 2) a language model with interleaved cross-modality fusion layers to interpret instructions and generate fine-grained responses conditioned on visual features; and 3) a tailored multi-stage training strategy that effectively bridges detection-specific learning with general vision-language understanding. We conduct extensive experiments on multiple benchmarks for open-vocabulary object detection (COCO, LVIS, ODinW), referring expression comprehension (RefCOCO/+/g, D3), and vision-language understanding (Flickr30k, VQAv2, GQA). The results show that UniPerception achieves strong open-world generalization and multi-modal understanding, outperforming the existing state-of-the-art methods and establishing itself as a unified, instruction-driven perception system.

Despite Transformers have achieved significant success in low-level vision tasks, they are constrained by computing self-attention with a quadratic complexity and limited-size windows. This limitation results in a lack of global receptive field across the entire image. Recently, State Space Models (SSMs) have gained widespread attention due to their global receptive field and linear complexity with respect to input length. However, integrating SSMs into low-level vision tasks presents two major challenges: 1) Relationship degradation of long-range tokens with a long-range forgetting problem by encoding pixel-by-pixel high-resolution images. 2) Significant redundancy in the existing multi-direction scanning strategy. To this end, we propose Hi-Mamba for image super-resolution (SR) to address these challenges, which unfolds the image with only a single scan. Specifically, the Global Hierarchical Mamba Block (GHMB) enables token interactions across the entire image, providing a global receptive field while leveraging a multi-scale structure to facilitate long-range dependency learning. Additionally, the Direction Alternation Module (DAM) adjusts the scanning patterns of GHMB across different layers to enhance spatial relationship modeling. Extensive experiments demonstrate that our Hi-Mamba achieves 0.2-0.27dB PSNR gains on the Urban100 dataset across different scaling factors compared to the state-of-the-art MambaIRv2 for SR. Moreover, our lightweight Hi-Mamba also outperforms lightweight SRFormer by 0.39dB PSNR for $\times 2$ SR.

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyperparameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an “initialization-expansion-merging” pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyperparameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3× faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://github.com/Osilly/TokenExpansion.

APT malware exploits HTTP to establish communication with a C & C server to hide their malicious activities. Thus, HTTP-based APT malware infection can be discovered by analyzing HTTP traffic. Recent methods have been dependent on the extraction of statistical features from HTTP traffic, which is suitable for machine learning. However, the features they extract from the limited HTTP-based APT malware traffic dataset are too simple to detect APT malware with strong randomness insufficiently. In this paper, we propose an innovative approach which could uncover APT malware traffic related to data exfiltration and other suspect APT activities by analyzing the header fields of HTTP traffic. We use the Referer field in the HTTP header to construct a web request graph. Then, we optimize the web request graph by combining URL similarity and redirect reconstruction. We also use a normal uncorrelated request filter to filter the remaining unrelated legitimate requests. We have evaluated the proposed method using 1.48 GB normal HTTP flow from clickminer and 280 MB APT malware HTTP flow from Stratosphere Lab, Contagiodump, and pcapanalysis. The experimental results have shown that the URL-correlation-based APT malware traffic detection method can correctly detect 96.08% APT malware traffic, and its recall rate is 98.87%. We have also conducted experiments to compare our approach against Jiang’s method, MalHunter, and BotDet, and the experimental results have confirmed that our detection approach has a better performance, the accuracy of which reached 96.08% and the F1 value increased by more than 5%.

Robots have been proposed to reduce the costs of the provision of healthcare in rural settings, but as yet little research has tested this. This study investigated the feasibility and cost-effectiveness of a robot measuring routine vital signs in a family medicine clinic in a rural setting. The length of patient consultations was compared before (N = 85 patients) and after a robot was deployed in the clinic (N = 48 patients). A Cafero touchscreen robot took the patient's vital signs prior to the consultation and transferred the results to the medical professional's computer. Time-savings were calculated in New Zealand dollar terms and compared to the costs of the robot and its maintenance. Results showed that consultation lengths were cut by 18% on average (3 minutes and 13 seconds). If 20% of the clinics' annual consultations were augmented with the robot this translates to a total annual savings of NZ$19075. The annual cost of the robot was calculated to be NZ$9400 overs 5 years. Present value calculations of Benefit Cost result in a Benefit Cost ratio of 2.3. These results support the cost-effectiveness of the robot in a rural medical clinic. Further research is needed to improve the services provided by the robot and test it in a larger trial.