In this article, a novel adaptive controller is designed for Euler-Lagrangian systems under predefined time-varying state constraints. The proposed controller could achieve this objective without a priori knowledge of...
详细信息
Real-world environment can be highly dynamic causing substantial domain shifts. Such real-world domain shifts can span over time with domain changes across multiple domains, manifested into the pertinent content or st...
详细信息
Real-world environment can be highly dynamic causing substantial domain shifts. Such real-world domain shifts can span over time with domain changes across multiple domains, manifested into the pertinent content or style changes, or both, where content may refer to underlying image layout and styles are domain-specific such as color and texture. Performance of safety-critical applications, especially robust object detection system in autonomous driving, must adapt to such test-time domain shifts. However, our empirical analysis shows existing domain adaptation and generalization methods fail to fit the domain changes with substantial style or content shifts. In this paper, we first analyze and investigate effective solutions to overcome domain overfitting for robust object detection without the above shortcomings. To simultaneously address temporal and multiple domain shifts, we propose a continual test-time generalizable domain adaptation (CoTGA) method for robust object detection: 1) the domain-invariant training (DIT) module leverages the Normalization Perturbation (NP) method to initialize a style-invariant object detection model, by perturbing the channel statistics of source domain low-level features to synthesize various latent styles. The trained deep model can perceive diverse potential domains and generalizes well even without observations of target domain data in training; 2) the test-time adaptation (TTA) module updates the DIT-trained model online during inference, through the consistency regularization between predictions of the weakly and strongly augmented unlabeled images. TTA addresses the content discrepancies problem of the DIT-initialized generalizable model; 3) the generalizable weights preservation (GWP) module keeps the learned generalizable weights to avoid domain overfitting in generalization across multiple domains. Extensive experiments demonstrate these three modules collaboratively enable a deep model to generalize well under challengin
Test-Time Adaptation (TTA) aims to provide a deployed agent capable of adapting to the target domain distribution using only unlabeled test data. Most existing TTA methods have achieved success under mild conditions, ...
详细信息
ISBN:
(数字)9798350349184
ISBN:
(纸本)9798350349191
Test-Time Adaptation (TTA) aims to provide a deployed agent capable of adapting to the target domain distribution using only unlabeled test data. Most existing TTA methods have achieved success under mild conditions, such as independently sampled data from a single or multiple static domains. However, these attempts may cause the deployed agent to fail in dynamic scenarios, where the test environment undergoes continuous changes over time. Previous TTA methods attempt to improve the quality of pseudo-labels by designing data augmentation strategies based on domain information. However, this violates the TTA paradigm, i.e., no characteristics of the dataset can be known in advance. Motivated by this, we propose a Robust Dual-stream Perturbation Test-time adaptation approach, called RDPT, to further stabilize the deployed agent from two aspects: (1) boost the robustness to noisy samples by encouraging the model to be consistent with its original image-level perturbation samples; (2) dynamically filtering samples with high entropy values, taking into account the discrepancy between the original and perturbation samples. Extensive experiments on the CIFAR10C and CIFAR100C benchmarks demonstrate the effectiveness of our method in dynamic scenarios, which is also easy to implement and deploy.
1
HerStory project addresses the need of European Union (EU) to combat gender-based stereotypes, a priority underscored by the EU Council. Also, it adheres to the main aim of the EU Gender Equality strategy 2020-2025, o...
详细信息
Image inpainting is a technique to modify an image by removing/fill-up the undesired region(s) in a visually plausible manner. With the advancement of cloud applications, the cloud service providers (CSPs) provide ima...
详细信息
The structural characterization of protein sequences is one of the most common problems in biology. This task is usually facilitated by the accurate Three-Dimensional (3-D) structure of the protein. This paper was car...
详细信息
API-driven chatbot systems are increasingly integral to software engineering applications, yet their effectiveness hinges on accurately generating and executing API calls. This is particularly challenging in scenarios...
详细信息
Representational transfer from publicly available models is a promising technique for improving medical image classification, especially in long-tailed datasets with rare diseases. However, existing methods often over...
详细信息
Recent advances in self-supervised learning (SSL) in computervision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image vie...
详细信息
Supervised deep learning methods require a large repository of annotated data;hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. ...
详细信息
暂无评论