Related papers: Multi-Granularity Alignment Domain Adaptation for …

Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in…

Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. However, image classification and object detection are essentially different…

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a…

Adapting visual object detectors to operational target domains is a challenging task, commonly achieved using unsupervised domain adaptation (UDA) methods. Recent studies have shown that when the labeled dataset comes from multiple source…

Recent works in domain adaptation always learn domain invariant features to mitigate the gap between the source and target domains by adversarial methods. The category information are not sufficiently used which causes the learned domain…

The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines. This problem will never be solved without algorithms able to adapt and generalize across visual domains.…

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of…

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…

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a…

Domain adaptation in object detection is critical for real-world applications where distribution shifts degrade model performance. Security X-ray imaging presents a unique challenge due to variations in scanning devices and environmental…

Domain adaptation aims to leverage information from the source domain to improve the classification performance in the target domain. It mainly utilizes two schemes: sample reweighting and feature matching. While the first scheme allocates…

Real-world object detectors are often challenged by the domain gaps between different datasets. In this work, we present the Conditional Domain Normalization (CDN) to bridge the domain gap. CDN is designed to encode different domain inputs…

Domain gaps between training data (source) and real-world environments (target) often degrade the performance of object detection models. Most existing methods aim to bridge this gap by aligning features across source and target domains but…

Despite outstanding performance on public benchmarks, face recognition still suffers due to domain mismatch between training (source) and testing (target) data. Furthermore, these domains are not shared classes, which complicates domain…

Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. Although the topic has attracted attention recently, current approaches all rely on the…

Supervised learning is often used to count objects in images, but for counting small, densely located objects, the required image annotations are burdensome to collect. Counting plant organs for image-based plant phenotyping falls within…

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been…

Recent advances in domain adaptation reveal that adversarial learning on deep neural networks can learn domain invariant features to reduce the shift between source and target domains. While such adversarial approaches achieve domain-level…

Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly,…