Related papers: Dual Path Learning for Domain Adaptation of Semant…

Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data. It has been applied effectively to domain adaptation (DA) on images and videos. It is still unknown if and how it can be leveraged for…

Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source domains may be very expensive, making complete labeling as…

One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations,…

Domain Adaptation (DA) is important for deep learning-based medical image segmentation models to deal with testing images from a new target domain. As the source-domain data are usually unavailable when a trained model is deployed at a new…

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of…

Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained…

We propose a domain adaptation approach for object detection. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to changes in the high-level…

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic…

Semantic segmentation of remote sensing images is a challenging and hot issue due to the large amount of unlabeled data. Unsupervised domain adaptation (UDA) has proven to be advantageous in incorporating unclassified information from the…

Domain generalization involves learning a classifier from a heterogeneous collection of training sources such that it generalizes to data drawn from similar unknown target domains, with applications in large-scale learning and personalized…

Graph domain adaptation has recently enabled knowledge transfer across different graphs. However, without the semantic information on target graphs, the performance on target graphs is still far from satisfactory. To address the issue, we…

We consider the problem of unsupervised domain adaptation in semantic segmentation. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy…

Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in…

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of cross-domain lane…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in some uncommon conditions. In this paper, we present a new framework…

The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For…

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…