Related papers: Adversarial Domain Adaptation for Action Recogniti…
Semantic segmentation of nighttime images plays an equally important role as that of daytime images in autonomous driving, but the former is much more challenging due to poor illuminations and arduous human annotations. In this paper, we…
Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through…
This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target…
Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Given pre-segmented videos, the task is to recognize actions…
Adversarial training is a useful approach to promote the learning of transferable representations across the source and target domains, which has been widely applied for domain adaptation (DA) tasks based on deep neural networks. Until very…
We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled source domain to an…
Increasingly, human behavior is captured on mobile devices, leading to an increased interest in automated human activity recognition. However, existing datasets typically consist of scripted movements. Our long-term goal is to perform…
Deep models trained on large-scale RGB image datasets have shown tremendous success. It is important to apply such deep models to real-world problems. However, these models suffer from a performance bottleneck under illumination changes.…
We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on…
In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this…
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and challenging, we propose to exploit auxiliary unlabeled videos,…
Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation. From domain adaptation perspective, the key challenge is to learn…
Adapting semantic segmentation models to new domains is an important but challenging problem. Recently enlightening progress has been made, but the performance of existing methods are unsatisfactory on real datasets where the new target…
Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated.…
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features…
Unsupervised domain adaptation aims at transferring knowledge from the labeled source domain to the unlabeled target domain. Previous adversarial domain adaptation methods mostly adopt the discriminator with binary or $K$-dimensional output…
Unsupervised Domain Adaptation (UDA) methods aim to transfer knowledge from a labeled source domain to an unlabeled target domain. UDA has been extensively studied in the computer vision literature. Deep networks have been shown to be…
The advent of deep learning has brought an impressive advance to monocular depth estimation, e.g., supervised monocular depth estimation has been thoroughly investigated. However, the large amount of the RGB-to-depth dataset may not be…
Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways…
Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy to the training dataset which must resemble the images in…