Related papers: Learning Instance-Specific Adaptation for Cross-Do…

We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have shown superior performance over classical hand-crafted local…

In this paper we present a solution to the task of "unsupervised domain adaptation (UDA) of a given pre-trained semantic segmentation model without relying on any source domain representations". Previous UDA approaches for semantic…

Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…

Few-shot semantic segmentation (FSS) has achieved great success on segmenting objects of novel classes, supported by only a few annotated samples. However, existing FSS methods often underperform in the presence of domain shifts, especially…

We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation. The overall goal is fostering the development of adaptive learning systems…

Test-time adaptation (TTA) has increasingly been an important topic to efficiently tackle the cross-domain distribution shift at test time for medical images from different institutions. Previous TTA methods have a common limitation of…

Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains, e.g., with different styles. To address this problem, previous methods mainly use holistic…

Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions. However, as any data scientist…

Domain adaptation aims at improving model performance by leveraging the learned knowledge in the source domain and transferring it to the target domain. Recently, domain adversarial methods have been particularly successful in alleviating…

Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks. However, these methods focus only on global distribution adaptation and ignore distribution…

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…

Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard…

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

This thesis contributes to the mathematical foundation of domain adaptation as emerging field in machine learning. In contrast to classical statistical learning, the framework of domain adaptation takes into account deviations between…

Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the…

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…

Post-training quantization methods use a set of calibration data to compute quantization ranges for network parameters and activations. The calibration data usually comes from the training dataset which could be inaccessible due to…

Large language models (LLMs) have showcased their capability with few-shot inference known as in-context learning. However, in-domain demonstrations are not always readily available in real scenarios, leading to cross-domain in-context…

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this…