Related papers: Domain-General Crowd Counting in Unseen Scenarios
Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works on domain adaptation simplify the setting and access…
Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data. Toward addressing this challenge, we consider the domain generalization…
Domain generalization (DG) is an important problem that learns a model which generalizes to unseen test domains leveraging one or more source domains, under the assumption of shared label spaces. However, most DG methods assume access to…
Magnetic resonance (MR) imaging, including cardiac MR, is prone to domain shift due to variations in imaging devices and acquisition protocols. This challenge limits the deployment of trained AI models in real-world scenarios, where…
Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scenarios. Since data…
Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple annotated source domains. When the source domains are…
Most research designing novel predictive models, or employing existing ones, assumes that training and testing data are independent and identically distributed. In practice, the data encountered at serving time often deviate from the…
Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels. Existing approaches mainly suffer from the extreme density variances. Such density pattern shift…
In this paper, we consider the problem of crowd counting in images. Given an image of a crowded scene, our goal is to estimate the density map of this image, where each pixel value in the density map corresponds to the crowd density at the…
Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to…
Few-shot counting estimates the number of target objects in an image using only a few annotated exemplars. However, domain shift severely hinders existing methods to generalize to unseen scenarios. This falls into the realm of single domain…
Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…
Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e.g., public parks, long subway platforms, or event spaces)…
Deep models trained on source domain lack generalization when evaluated on unseen target domains with different data distributions. The problem becomes even more pronounced when we have no access to target domain samples for adaptation. In…
Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…
The generalization of deep neural networks to unknown domains is a major challenge despite their tremendous progress in recent years. For this reason, the dynamic area of domain generalization (DG) has emerged. In contrast to unsupervised…
How can we apply human feedback into generative model? As answer of this question, in this paper, we show the method applied on denoising problem and domain adaptation using human feedback. Deep generative models have demonstrated…
Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain…
Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would…
Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are…