Related papers: Aligning Correlation Information for Domain Adapta…
Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data…
Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…
Domain adaptation is an active area of research driven by the growing demand for robust machine learning models that perform well on real-world data. Adversarial learning for deep neural networks (DNNs) has emerged as a promising approach…
Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos. However, the problem of cross-domain action recognition, where training and testing videos are drawn from…
Assuming the source label space subsumes the target one, Partial Video Domain Adaptation (PVDA) is a more general and practical scenario for cross-domain video classification problems. The key challenge of PVDA is to mitigate the negative…
Domain adaptation (DA) is transfer learning which aims to learn an effective predictor on target data from source data despite data distribution mismatch between source and target. We present in this paper a novel unsupervised DA method for…
Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In…
In Domain Adaptation (DA), where the feature distributions of the source and target domains are different, various distance-based methods have been proposed to minimize the discrepancy between the source and target domains to handle the…
In this report, we present the technical details of our submission to the 2022 EPIC-Kitchens Unsupervised Domain Adaptation (UDA) Challenge. Existing UDA methods align the global features extracted from the whole video clips across the…
There has been abundant work in unsupervised domain adaptation for semantic segmentation (DAS) seeking to adapt a model trained on images from a labeled source domain to an unlabeled target domain. While the vast majority of prior work has…
Conventional cross-domain image-to-image translation or unsupervised domain adaptation methods assume that the source domain and target domain are closely related. This neglects a practical scenario where the domain discrepancy between the…
Domain adaptation is critical for success in new, unseen environments. Adversarial adaptation models applied in feature spaces discover domain invariant representations, but are difficult to visualize and sometimes fail to capture…
Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising,…
Existing deep learning methods of video recognition usually require a large number of labeled videos for training. But for a new task, videos are often unlabeled and it is also time-consuming and labor-intensive to annotate them. Instead of…
This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on…
Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e.g., art, real, painting, quickdraw, etc. We argue that this is not realistic as it is implausible to define the…
For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and…
Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First,…
The recent advances in deep neural networks have convincingly demonstrated high capability in learning vision models on large datasets. Nevertheless, collecting expert labeled datasets especially with pixel-level annotations is an extremely…
Semantic segmentation requires a lot of training data, which necessitates costly annotation. There have been many studies on unsupervised domain adaptation (UDA) from one domain to another, e.g., from computer graphics to real images.…