Related papers: RADA: Robust Adversarial Data Augmentation for Cam…

The success of supervised classification of remotely sensed images acquired over large geographical areas or at short time intervals strongly depends on the representativity of the samples used to train the classification algorithm and to…

Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. However, they are known to be sensitive to adverse weather conditions such as rain, snow and fog due…

Visual relocalization aims to estimate the pose of a camera from one or more images. In recent years deep learning based pose regression methods have attracted many attentions. They feature predicting the absolute poses without relying on…

Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial…

Autonomous driving systems are highly dependent on sensors like cameras, LiDAR, and inertial measurement units (IMU) to perceive the environment and estimate their motion. Among these sensors, perception-based sensors are not protected from…

We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data. Our method is based on invariant instance feature learning but is tailored for…

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization…

Deep learning models can perform well when evaluated on images from the same distribution as the training set. However, applying small perturbations in the forms of noise, artifacts, occlusions, blurring, etc. to a model's input image and…

Current methods based on Neural Radiance Fields fail in the low data limit, particularly when training on incomplete scene data. Prior works augment training data only in next-best-view applications, which lead to hallucinations and model…

Image recognition models that work in challenging environments (e.g., extremely dark, blurry, or high dynamic range conditions) must be useful. However, creating training datasets for such environments is expensive and hard due to the…

High-autonomy vehicle functions rely on machine learning (ML) algorithms to understand the environment. Despite displaying remarkable performance in fair weather scenarios, perception algorithms are heavily affected by adverse weather and…

Robust high-dimensional data processing has witnessed an exciting development in recent years, as theoretical results have shown that it is possible using convex programming to optimize data fit to a low-rank component plus a sparse outlier…

Deep learning models have a large number of free parameters that must be estimated by efficient training of the models on a large number of training data samples to increase their generalization performance. In real-world applications, the…

The development of fair and ethical AI systems requires careful consideration of bias mitigation, an area often overlooked or ignored. In this study, we introduce a novel and efficient approach for addressing biases called Targeted Data…

Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection…

Data modification, either via additional training datasets, data augmentation, debiasing, and dataset filtering, has been proposed as an effective solution for generalizing to out-of-domain (OOD) inputs, in both natural language processing…

Reliable localization is crucial for autonomous robots to navigate efficiently and safely. Some navigation methods can plan paths with high localizability (which describes the capability of acquiring reliable localization). By following…

Random data augmentations (RDAs) are state of the art regarding practical graph neural networks that are provably universal. There is great diversity regarding terminology, methodology, benchmarks, and evaluation metrics used among existing…

Domain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address this by minimising domain discrepancy during training, but the discrepancy estimates suffer…

Recognition of the surrounding environment using a camera is an important technology in Advanced Driver-Assistance Systems and Autonomous Driving, and recognition technology is often solved by machine learning approaches such as deep…