相关论文: From Synthetic to Real: Unsupervised Domain Adapta…

Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degradation due to the…

Accurate lane detection, a crucial enabler for autonomous driving, currently relies on obtaining a large and diverse labeled training dataset. In this work, we explore learning from abundant, randomly generated synthetic data, together with…

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal…

Animal pose estimation is an important but under-explored task due to the lack of labeled data. In this paper, we tackle the task of animal pose estimation with scarce annotations, where only a small set of labeled data and unlabeled images…

Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are…

Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…

The performance of state-of-the-art object detectors degrades significantly under adverse weather, causing a safety-critical domain shift problem for autonomous vehicles. Recent efforts address this problem by relying on synthetic data to…

Domain adaptation (DA) is a representation learning methodology that transfers knowledge from a label-sufficient source domain to a label-scarce target domain. While most of early methods are focused on unsupervised DA (UDA), several…

Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques…

Estimating the pose of animals can facilitate the understanding of animal motion which is fundamental in disciplines such as biomechanics, neuroscience, ethology, robotics and the entertainment industry. Human pose estimation models have…

Unsupervised domain adaptation (UDA) enables knowledge transfer from the labelled source domain to the unlabeled target domain by reducing the cross-domain discrepancy. However, most of the studies were based on direct adaptation from the…

In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment…

In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing…

Accurate product information is critical for e-commerce stores to allow customers to browse, filter, and search for products. Product data quality is affected by missing or incorrect information resulting in poor customer experience. While…

In this paper, we are interested in pose estimation of animals. Animals usually exhibit a wide range of variations on poses and there is no available animal pose dataset for training and testing. To address this problem, we build an animal…

Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically…

For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. However, this may still incur a large domain gap due to the lack…

Semantic part segmentation provides an intricate and interpretable understanding of an object, thereby benefiting numerous downstream tasks. However, the need for exhaustive annotations impedes its usage across diverse object types. This…

Multi-animal pose estimation is essential for studying animals' social behaviors in neuroscience and neuroethology. Advanced approaches have been proposed to support multi-animal estimation and achieve state-of-the-art performance. However,…

Obtaining labelled data to train deep learning methods for estimating animal pose is challenging. Recently, synthetic data has been widely used for pose estimation tasks, but most methods still rely on supervised learning paradigms…