Related papers: Unsupervised Domain Adaptation with Contrastive Le…
Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on limited datasets, or…
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object…
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…
Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its…
Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the…
Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…
The vast amount of unlabeled multi-temporal and multi-sensor remote sensing data acquired by the many Earth Observation satellites present a challenge for change detection. Recently, many generative model-based methods have been proposed…
To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning. However, such…
Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less…
In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets. However, this comes at the cost of training multiple models or requiring complex…
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…
This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The…
In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive…
Semi-supervised learning has the potential to improve the data-efficiency of training data-hungry deep neural networks, which is especially important for medical image analysis tasks where labeled data is scarce. In this work, we present a…
Semi-supervised medical image segmentation has shown promise in training models with limited labeled data and abundant unlabeled data. However, state-of-the-art methods ignore a potentially valuable source of unsupervised semantic…
The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…
Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated…
Mitochondria segmentation in electron microscopy images is essential in neuroscience. However, due to the image degradation during the imaging process, the large variety of mitochondrial structures, as well as the presence of noise,…
Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, such methods typically…
Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorporating SSL. The intuition is to enforce instance-level…