Zhen Wei

We propose DiffGeo, a latent space diffusion-based generative framework for aerodynamic design space exploration under extreme data scarcity. DiffGeo combines a learned latent space model for automatic shape parameterization with a diffusion sampler to directly generate novel, geometry-valid, and controllable designs. We validate the approach on a series of case studies: i) a 2D airfoil generation benchmark, where DiffGeo’s latent diffusion model is compared against GAN- and VAE-based baselines in terms of sample quality, diversity, and constraint adherence under limited data; ii) integration into a surrogate-based optimization pipeline, where DiffGeo’s conditional sampling produces task-informed airfoil data that improve both surrogate modeling and optimization performance; and iii) extension to 3D turbomachinery blade prototyping, where DiffGeo generates realistic and high-performance blade geometries from a small set of reference designs. Throughout these investigations, DiffGeo achieves high-quality and diverse shape generation with at least an order of magnitude less data than alternatives, decouples geometry representation from design targets for flexible reuse, and seamlessly incorporates complex design constraints via energy-based conditioning. These capabilities demonstrate DiffGeo’s potential to enhance early-stage design by automating design space exploration—improving efficiency, expanding design diversity, and embedding engineering knowledge through controllable guidance.

Traditional aerodynamic shape optimization (ASO) is costly and time-intensive, requiring extensive manual tuning for parameterization to define the design space and manipulate geometries. Conventional parameterization methods limit flexibility and demand specialized knowledge, making efficient ASO challenging. We introduce the deep geometric mapping (DeepGeo) model, a neural-network-based approach that automates parameterization, accelerating ASO and reducing costs. By leveraging the expressive capacity of neural networks, DeepGeo handles large shape deformation while preserving global surface smoothness, allowing efficient optimization in high-dimensional design spaces. Eliminating the need for training datasets and manual hyperparameter tuning and integrating computational fluid dynamics (CFD) mesh deformation, DeepGeo significantly lowers ASO’s implementation complexity and cost. Case studies, including two-dimensional circle, Common Research Model wing, and blended-wing–body aircraft optimization, validate DeepGeo’s effectiveness, achieving results comparable to state-of-the-art free-form deformation with minimal manual intervention. This work positions DeepGeo as a novel and effective parameterization framework that streamlines the workflow and reduces implementation complexity in advanced ASO.

Mesh manipulation is central to computational fluid dynamics. However, creating appropriate computational meshes often involves substantial manual intervention that has to be repeated each time the target shape changes. To address this problem, we propose an autodecoder-based latent representation approach. Human prior knowledge is embedded into learned geometric patterns, which eliminates the need for further handcrafting. Furthermore, the resulting computational meshes are differentiable with respect to the model parameters, which makes it suitable for inclusion in end-to-end trainable pipelines. We apply the model on two-dimensional airfoils to demonstrate its ability to handle various tasks.

Person retrieval largely relies on the appearance features of pedestrians. This task is rather more difficult in surveillance videos due to the limitations of extracting robust appearance features brought by the cross-view and cross-camera data with lower image resolution, motion blur, occlusion and other kinds of image degradation. To build up a more reliable person retrieval system, recent works introduced appearance attribute models to describe and distinguish different persons with high-level semantic concepts. Despite the progress of previous works, the value of utilizing appearance attributes is still under-explored. On one hand, existing methods lack for concise and precise attribute representations that are specific for each attribute category and, in the meantime, are able to filter noisy information in irrelevant spatial locations and useless patterns. On the other hand, correlation and reasoning between different attributes are neglected, which could generate more useful information and add more robustness to the retrieval system. In this paper, we propose an Attribute Mining and Reasoning (AMR) framework which is capable to handle the issues in question. The AMR makes better use of appearance attributes with two main components. First, the AMR disentangles the representations of different attributes by localizing their spatial positions and identifying their effective patterns in a weakly supervised manner. To achieve more reliable localization, we propose the Attribute Localization Ensemble (ALE) module that is consisted of multiple localization heads and a voting mechanism. Second, we introduce the Attribute Reasoning (AR) module to correlate different attributes together with the global appearance features and discover their latent relations to generate more comprehensive descriptions of pedestrians. Extensive experiments on DukeMTMC-ReID and Market-1501 datasets demonstrate the effectiveness of the proposed AMR framework as well as its superiority over the existing state-of-the-art methods. The AMR model also shows great generalization ability on the unseen CUHK03 dataset when it is only trained on Market-1501 dataset.

Person retrieval aims at effectively matching the pedestrian images over an extensive database given a specified identity. As extracting effective features is crucial in a high-performance retrieval system, recent significant progress was achieved by part-based models that have constructed robust local representations on top of vertically striped part features. However, this kind of models use predefined partitioning strategies, making the number and size of each partition identical even when input images vary a lot. This unchangeable setting usually leads to less flexibility and robustness in capturing visual variance. The primary reason for such a negative effect is that a fixed partitioning strategy is unable to deal with (a) the significant variance from pose, illumination and viewpoint which is common in a pedestrian image dataset, and (b) also the inference error and misalignment of human bodies introduced by the prepositive pedestrian detection module or human pose estimation module. In this paper, we tackle this problem via introducing the novel Adaptive Partition Network (APN). The APN utilizes deep reinforcement learning and applies an agent to generate optimal partitioning strategies dynamically for different input images. The agent inside the APN is optimized with the policy gradient algorithm and maximizes the reward of choosing the best partition setting. By leveraging the supervision cues from the objective partitioning strategies that are generated on a set of held-out training images, the agent is trained jointly with other parts of APN, which ensures the APN's robustness and generalization ability. Extensive experimental results on multiple datasets, including CUHK03, DukeMTMC and Market-1501, demonstrate the superiority of APN over the state-of-the-art models.

In this paper, we propose a design scheme for deep learning networks in the face parsing task with promising accuracy and real-time inference speed. By analyzing the differences between the general image parsing task and face parsing task, we first revisit the structure of traditional FCN and make improvements to adapt to the unique properties of the face parsing task. Especially, the concept of Normalized Receptive Field is proposed to give more insights on designing the network. Then, a novel loss function called Statistical Contextual Loss is introduced, which integrates richer contextual information and regularizes features during training. For further model acceleration, we propose a semi-supervised distillation scheme that effectively transfers the learned knowledge to a lighter network. Extensive experiments on LFW and Helen dataset demonstrate the significant superiority of the new design scheme on both efficacy and efficiency.

Image retargeting has been applied to display images of any size via devices with various resolutions (e.g., cell phone and TV monitors). To fit an image with the target resolution, certain unimportant regions need to be deleted or distorted, and the key problem is to determine the importance of each pixel. Existing methods predict pixel-wise importance in a bottom-up manner via eye fixation estimation or saliency detection. In contrast, the proposed algorithm estimates the pixel-wise importance based on a top-down criterion where the target image maintains the semantic meaning of the original image. To this end, several semantic components corresponding to foreground objects, action contexts, and background regions are extracted. The semantic component maps are integrated by a classification guided fusion network. Specifically, the deep network classifies the original image as object or scene oriented, and fuses the semantic component maps according to classification results. The network output, referred to as the semantic collage with the same size as the original image, is then fed into any existing optimization method to generate the target image. Extensive experiments are carried out on the RetargetMe data set and S-Retarget database developed in this paper. Experimental results demonstrate the merits of the proposed algorithm over the state-of-the-art image retargeting methods.

Recent advances in wireless networking technologies and mobile computing devices have engendered a new paradigm of computing, mobile computing. In the meantime, applications on these mobile devices also present some challenges to software designers. In order to cope with these challenges, many research efforts have been focused on a new middleware system that can support the requirements imposed by mobility. In this paper, we investigate some key issues in mobile middleware systems and introduce several basic concepts related to mobile middleware. In addition, we also discuss the technical requirements that mobile middleware systems have to meet. Finally, we conclude the paper and present the future research direction of mobile middleware system.