Related papers: Informative Data Mining for One-Shot Cross-Domain …
Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acquire. Therefore, previous works pre-train their models on…
The network trained for domain adaptation is prone to bias toward the easy-to-transfer classes. Since the ground truth label on the target domain is unavailable during training, the bias problem leads to skewed predictions, forgetting to…
Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically…
The increasing relevance of panoptic segmentation is tied to the advancements in autonomous driving and AR/VR applications. However, the deployment of such models has been limited due to the expensive nature of dense data annotation, giving…
Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…
While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…
State-of-the-art 3D semantic segmentation models are trained on off-the-shelf public benchmarks, but they will inevitably face the challenge of recognition accuracy drop when these well-trained models are deployed to a new domain. In this…
Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…
Semantic segmentation is key in autonomous driving. Using deep visual learning architectures is not trivial in this context, because of the challenges in creating suitable large scale annotated datasets. This issue has been traditionally…
Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and…
Domain adaptation is critical for success when confronting with the lack of annotations in a new domain. As the huge time consumption of labeling process on 3D point cloud, domain adaptation for 3D semantic segmentation is of great…
Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to…
We develop an algorithm to improve the performance of a pre-trained model under concept shift without retraining the model from scratch when only unannotated samples of initial concepts are accessible. We model this problem as a domain…
In unsupervised domain adaptive (UDA) semantic segmentation, the distillation based methods are currently dominant in performance. However, the distillation technique requires complicate multi-stage process and many training tricks. In this…
Domain adaptive semantic segmentation is the task of generating precise and dense predictions for an unlabeled target domain using a model trained on a labeled source domain. While significant efforts have been devoted to improving…
Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…
Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict…
In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation. We propose domain adaptation by sampling and exploiting only a meaningful subset from source data for training. Our…
The recent advances in deep learning predominantly construct models in their internal representations, and it is opaque to explain the rationale behind and decisions to human users. Such explainability is especially essential for domain…