Single-Domain Generalized Object Detection (S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on data augmentation strategies, including a composition of visual transformations, to enhance the detector's generalization ability. However, the absence of real-world prior knowledge hinders data augmentation from contributing to the diversity of training data distributions. To address this issue, we propose PhysAug, a novel physical model-based non-ideal imaging condition data augmentation method, to enhance the adaptability of the S-DGOD tasks. Drawing upon the principles of atmospheric optics, we develop a universal perturbation model that serves as the foundation for our proposed PhysAug. Given that visual perturbations typically arise from the interaction of light with atmospheric particles, the image frequency spectrum is harnessed to simulate real-world variations during training. This approach fosters the detector to learn domain-invariant representations, thereby enhancing its ability to generalize across various settings. Without altering the network architecture or loss function, our approach significantly outperforms the state-of-the-art across various S-DGOD datasets. In particular, it achieves a substantial improvement of 7.3% and 7.2% over the baseline on DWD and Cityscape-C, highlighting its enhanced generalizability in real-world settings.

In modern manufacturing industry featured with automation and flexibility, the intelligent tool management for Computer Numeric Control (CNC) machine plays an essential role in manufacturing automation. The automatic tool recognition in terms of geometric shapes, materials and usage functions could facilitate the seamless integration with downstream process planning and scheduling processes. In this paper, a intelligent tool recognition system is proposed with a novel hybrid framework of multi-channel deep learning network with non-iterative and fast feedforward neural network to meet high efficiency and accuracy requirement in intelligent manufacturing. The combination of the fine-tuning Convolutional Neural Networks (CNNs) with the random parameter assignment mechanism of Extreme Learning Machines (ELMs) reach a balance in accurate feature extraction and fast recognition. In the proposed hybrid framework, features extracted from efficient CNNs are aggregated into robust ELM auto-encoders (ELM-AEs) to generate the compact but rich feature information, which are then feed to the subsequent single layer ELM network for tool recognition. The performance of proposed framework is verified on several standardized 3D shape retrieval and classification dataset, as well as on a self-constructed multi-view 3D data represented tool library database. Numerical experiments reveal a promising application perspective of proposed intelligent recognition system on manufacturing automation.

Deep learning has achieved remarkable success in numerous computer vision tasks. However, recent research reveals that deep neural networks are vulnerable to natural perturbations from poor visibility conditions, limiting their practical applications. While several studies have focused on enhancing model robustness in poor visibility conditions through techniques such as image restoration, data augmentation, and unsupervised domain adaptation, these efforts are predominantly confined to specific scenarios and fail to address multiple poor visibility scenarios encountered in real-world settings. Furthermore, the valuable prior knowledge inherent in poor visibility images is seldom utilized to aid in resolving high-level computer vision tasks. In light of these challenges, we propose a novel deep learning paradigm designed to bolster the robustness of object recognition across diverse poor visibility scenes. By observing the prior information in diverse poor visibility scenes, we integrate a feature matching module based on this prior knowledge into our proposed learning paradigm, aiming to facilitate deep models in learning more robust generic features at shallow levels. Moreover, to further enhance the robustness of deep features, we employ an adversarial learning strategy based on mutual information. This strategy combines the feature matching module to extract task-specific representations from low visibility scenes in a more robust manner, thereby enhancing the robustness of object recognition. We evaluate our approach on self-constructed datasets containing diverse poor visibility scenes, including visual blur, fog, rain, snow, and low illuminance. Extensive experiments demonstrate that our proposed method yields significant improvements over existing solutions across various poor visibility conditions.

Accurate visual detection under poor illuminance is arguably an important and challenging practice for robot monitoring. The purpose of this study is to build detectors for inspection robot under nonuniform and poor lighting conditions. To this end, we propose an Unsupervised Lighting Reflectance Estimation framework for dark image detection (ULRE-Net). Based on lightness-color consistency, the “true color" of objects merely depends on the reflectance regardless of the variations of illuminance. The proposed ULRE-Net extracts robust features for detection by estimating a simple and differentiable expression of reflectance, and the method formulates reflectance estimation in an unsupervised learning manner without relying on image pairs. Thorough experiments are conducted to validate the veracity and generality of the proposed method over existing ones.

Embodied PointGoal navigation is a fundamental task for embodied agents. Recent works have shown that the performance of the embodied navigation agent degrades significantly in the presence of visual corruption, including Spatter, Speckle Noise, and Defocus Blur, showing the weak robustness of the agent. To improve the robustness of embodied navigation agents to various visual corruptions, we propose a navigation framework called Regularized Denoising Masked AutoEncoders Navigation (RDMAE-Nav). In a nutshell, RDMAE-Nav mainly consists of two modules: a visual module and a policy module. In the visual module, a self-supervised pretraining method, dubbed Regularized Denoising Masked AutoEncoders (RDMAE), is designed to enable the Vision Transformers (ViT)-based visual encoder to learn robust representations. The bidirectional Kullback–Leibler divergence is introduced in RDMAE as the regularization term for a denoising masked modeling task. Specifically, RDMAE mitigates the gap between clean and noisy image representations by minimizing the bidirectional Kullback–Leibler divergence. Then, the visual encoder is pretrained by RDMAE. In contrast to existing works, RDMAE-Nav applies denoising masked visual pretraining for PointGoal navigation to improve robustness to various visual corruptions. Finally, the pretrained visual encoder with frozen weights is applied to extract robust visual representations for policy learning in the RDMAE-Nav. Extensive experiments show that RDMAE-Nav performs competitively compared with state of the arts (SOTAs) on various visual corruptions. In detail, RDMAE-Nav performs the absolute improvement: 28.2% in SR and 23.68% in SPL under Spatter; 2.28% in SR and 6.41% in SPL under Speckle Noise; and 9.46% in SR and 9.55% in SPL under Defocus Blur.

Category-level object pose estimation has attracted attention in robotics and augmented reality, as it enables generalization to unseen instances within known categories. However, significant intra-category shape variations and the complexity of effectively integrating geometric and visual information pose challenges to accurate pose and size estimation in vision measurement. Leveraging the widespread availability of affordable RGB-D sensors, this study explores an effective strategy for extracting and fusing appearance and geometric features to improve estimation performance. We introduce a vision foundation model for robust appearance feature extraction and propose a novel point-to-patch feature fusion strategy that leverages pixel-wise RGB-D correspondence to concatenate patch-level appearance features with point-level geometric features. The estimation process follows a two-stage paradigm, where object translation and size are first predicted, followed by rotation estimation guided by an auxiliary branch designed to facilitate learning of rotation-aware transformations. The proposed method achieves state-of-the-art performance on the CAMERA25 and REAL275 datasets, with enhanced generalization on the Wild6D dataset. Additionally, it supports real-time inference at 34 FPS on a single NVIDIA RTX A6000 GPU.