相关论文: Bridging the Generalization Gap in Adverse Weather…

Semantic segmentation of land cover classes is fundamental for agricultural and economic development work, from sustainable forestry to urban planning, yet existing training datasets have significant limitations. To generate an open and…

Few shot learning is an important problem in machine learning as large labelled datasets take considerable time and effort to assemble. Most few-shot learning algorithms suffer from one of two limitations- they either require the design of…

Existing domain generalization methods for LiDAR semantic segmentation under adverse weather struggle to accurately predict "things" categories compared to "stuff" categories. In typical driving scenes, "things" categories can be dynamic…

This work studies deep metric learning under small to medium scale data as we believe that better generalization could be a contributing factor to the improvement of previous fine-grained image retrieval methods; it should be considered…

The ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions served as a rigorous platform to evaluate and benchmark state-of-the-art semantic segmentation models under challenging…

This paper presents a comprehensive evaluation of instance segmentation models with respect to real-world image corruptions as well as out-of-domain image collections, e.g. images captured by a different set-up than the training dataset.…

We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and target domains. However, the…

The increasing demand for autonomous machines in construction environments necessitates the development of robust object detection algorithms that can perform effectively across various weather and environmental conditions. This paper…

Generalized linear model with $L_1$ and $L_2$ regularization is a widely used technique for solving classification, class probability estimation and regression problems. With the numbers of both features and examples growing rapidly in the…

We demonstrate that recent advances in reinforcement learning (RL) combined with simple architectural changes significantly improves generalization on the ProcGen benchmark. These changes are frame stacking, replacing 2D convolutional…

Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range…

Global Storm-Resolving Models (GSRMs) have gained widespread interest because of the unprecedented detail with which they resolve the global climate. However, it remains difficult to quantify objective differences in how GSRMs resolve…

We investigated domain adaptive semantic segmentation in foggy weather scenarios, which aims to enhance the utilization of unlabeled foggy data and improve the model's adaptability to foggy conditions. Current methods rely on clear images…

Supervised learning is all about the ability to generalize knowledge. Specifically, the goal of the learning is to train a classifier using training data, in such a way that it will be capable of classifying new unseen data correctly. In…

In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge. Conventional ML models trained on clear weather data falter…

Challenges have become the state-of-the-art approach to benchmark image analysis algorithms in a comparative manner. While the validation on identical data sets was a great step forward, results analysis is often restricted to pure ranking…

The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image recognition models strongly degrades when evaluated on…

Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We…

This paper investigates enhancements to model-based methods for seasonal adjustment, with a particular focus on the state space modeling framework. It addresses limitations of the standard Decomp model; specifically, the tendency to produce…

Deep learning-based LiDAR odometry is crucial for autonomous driving and robotic navigation, yet its performance under adverse weather, especially snowfall, remains challenging. Existing models struggle to generalize across conditions due…