Object detection has become crucial due to its extensive applications across various industries. However, the data used to train these models is often sensitive and proprietary, raising significant concerns about its security and unauthorized usage. Unlearnable examples (UEs) represent a promising strategy to safeguard proprietary datasets by embedding imperceptible perturbations that degrade model performance when such data is used during training. This paper explores UEs tailored specifically for object detection tasks, which pose unique challenges due to the multi-task nature of object detection. We propose a novel framework that generates robust and effective UEs, and significantly degrades object detector performance while maintaining imperceptibility. Comprehensive experiments demonstrate the resilience of the proposed UEs against various countermeasures, underscoring their potential as a practical solution for protecting data in object detection.

Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from unauthorized exploration by adding small perturbations to data. However, such perturbations (e.g., noise, texture, color change) predominantly impact low-level features, making them vulnerable to common countermeasures. In contrast, semantic images with intricate shapes have a wealth of high-level features, making them more resilient to countermeasures and potential for producing robust unlearnable examples. In this paper, we propose a Deep Hiding (DH) scheme that adaptively hides semantic images enriched with high-level features. We employ an Invertible Neural Network (INN) to invisibly integrate predefined images, inherently hiding them with deceptive perturbations. To enhance data unlearnability, we introduce a Latent Feature Concentration module, designed to work with the INN, regularizing the intra-class variance of these perturbations. To further boost the robustness of unlearnable examples, we design a Semantic Images Generation module that produces hidden semantic images. By utilizing similar semantic information, this module generates similar semantic images for samples within the same classes, thereby enlarging the inter-class distance and narrowing the intra-class distance. Extensive experiments on CIFAR-10, CIFAR-100, and an ImageNet subset, against 18 countermeasures, reveal that our proposed method exhibits outstanding robustness for unlearnable examples, demonstrating its efficacy in preventing unauthorized data exploitation.

The platooning of electrified vehicles can improve vehicle performance by enhancing energy efficiency and safety. Nevertheless, studies focusing on control strategies for platoons usually ignore or over-simplify the powertrain in the vehicle dynamics model. Advanced powertrain control strategies for electrified vehicles show that efficient operation of the powertrain depends on the current vehicle status, such as the torque demand, vehicle speed, and battery state of charge. In addition, the operation of individual powertrains can affect platoon-level performance, and the relationship between powertrain operation and vehicle status can be highly nonlinear. In studies of platoons, the evaluation of vehicle performance usually requires the vehicle to converge to a static operating point or to follow a simple operating pattern. Ideal cases can help in the understanding and improvement of vehicle performance but may be less beneficial for applications in realistic cases that are more complex, e.g. in military operations. In this study, a platooning optimization problem is formulated for optimal performance between two locations, given the terrain grade and soil properties along the path. A high-fidelity powertrain model is constructed and embedded in a detailed platoon model. The drive schedule is specifically designed for a platoon of vehicles with an innovative hybrid electric powertrain to achieve minimum total energy consumption. Results show that the approach is able to reduce energy consumption and headway keeping errors.

We tackle the task of street-to-shop clothing image synthesis. Given a daily person image with a particular clothing item captured in the street scenario, we aim to synthesize the frontal facing view of that item in the shop scenario. This problem has the following challenges: 1) the distinct visual discrepancy between the street and shop scenario; 2) the severe shape deformation of clothing in the presence of an arbitrary human pose; 3) the preservation of fine-grained details during the process of clothing image generation. In this paper, we jointly solve these difficulties by proposing a Pose-Normalized and Appearance-Preserved Generative Adversarial Network (PNAP-GAN). More specifically, conditioned on the clothing-agnostic representation (i.e., clothing landmarks and semantic parsing map), we disentangle the shape and appearance synthesis in a coarse-to-fine framework. Moreover, a semantic embedding loss is introduced to guide the domain transfer in the semantic level (i.e., keeping the clothing attributes). With the synthesized frontal shop image, a pose-normalized representation in complementary to the domain-invariant feature learnt from the original street image are integrated to facilitate the problem of street-to-shop clothing retrieval. Extensive experiments conducted demonstrate the effectiveness of the proposed PNAP-GAN on generating high quality frontal-view images and the excellence of the learnt pose-normalized features on the retrieval task than existing methods. In addition, we demonstrate that the pose-normalized retrieval feature benefits the cross-scenario (i.e., street-to-shop) clothing image generation in a semantic-preserved manner.

Deep neural networks have demonstrated tremendous success in image classification, but their performance sharply degrades when evaluated on slightly different test data (e.g., data with corruptions). To address these issues, we propose a minimax approach to improve common corruption robustness of deep neural networks via Gaussian Adversarial Training. To be specific, we propose to train neural networks with adversarial examples where the perturbations are Gaussian-distributed. Our experiments show that our proposed GAT can improve neural networks' robustness to noise corruptions more than other baseline methods. It also outperforms the state-of-the-art method in improving the overall robustness to common corruptions.

An autoencoder that learns a latent space in an unsupervised manner has many applications in signal processing. However, the latent space of an autoencoder does not pursue the same clustering goal as Kmeans or GMM. A recent work proposes to artificially re-align each point in the latent space of an autoencoder to its nearest class neighbors during training (Song et al. 2013). The resulting new latent space is found to be much more suitable for clustering, since clustering information is used. Inspired by previous works (Song et al. 2013), in this letter we propose several extensions to this technique. First, we propose a probabilistic approach to generalize Song's approach, such that Euclidean distance in the latent space is now represented by KL divergence. Second, as a consequence of this generalization we can now use probability distributions as inputs rather than points in the latent space. Third, we propose using Bayesian Gaussian mixture model for clustering in the latent space. We demonstrated our proposed method on digit recognition datasets, MNIST, USPS and SHVN as well as scene datasets, Scene15 and MIT67 with interesting findings.