Deep neural networks (DNNs) have proven their capabilities in the past years and play a significant role environment perception for challenging application of automated driving. They are employed tasks such as detection, semantic segmentation, sensor fusion. Despite tremendous research efforts, several issues still need to be addressed that limit applicability DNNs The bad generalization unseen...

Enhancing model prediction confidence on target data is an important objective in Unsupervised Domain Adaptation (UDA). In this paper, we explore adversarial training penultimate activations, i.e., input features of the final linear classification layer. We show that strategy more efficient and better correlated with boosting than images or intermediate features, as used previous works. Further...

Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source and unlabeled domain. Classical UDA learning bounds show that risk is upper bounded by three terms: risk, distribution discrepancy, combined risk. Based on assumption small fixed value, methods based this bound only minimizing estimators of discrepancy. However, may increase when both est...

We propose an unsupervised domain adaptation (UDA) approach for white matter hyperintensity (WMH) segmentation, which uses Self-TRaining with Uncertainty DEpendent Label refinement (STRUDEL). Self-training has recently been introduced as a highly effective method UDA, is based on self-generated pseudo labels. However, labels can be very noisy and therefore deteriorate model performance. to pred...

LiDAR semantic segmentation is receiving increased attention due to its deployment in autonomous driving applications. As LiDARs come often with other sensors such as RGB cameras, multi-modal approaches for this task have been developed, which however suffer from the domain shift problem deep learning approaches. To address this, we propose a novel Unsupervised Domain Adaptation (UDA) technique...

Clustering is important for domain adaptive person re-identification(re-ID). A majority of unsupervised adaptation (UDA) methods conduct clustering on the target and then use generated pseudo labels training. Albeit important, pipeline adopted by current literature quite standard lacks consideration two characteristics re-ID, i.e., 1) a single has various feature distribution in multiple camera...

With the rapid development of remote sensing monitoring and computer vision technology, deep learning method has made a great progress to achieve applications such as earth observation, climate change even space exploration. However, model trained on existing data cannot be directly used handle new data, labeling is also time-consuming labor-intensive. Unsupervised Domain Adaptation (UDA) one s...