Related papers: A Prototype-Oriented Clustering for Domain Shift w…
Deep clustering has gained significant attention due to its capability in learning clustering-friendly representations without labeled data. However, previous deep clustering methods tend to treat all samples equally, which neglect the…
Unsupervised domain adaptation aims to train a classification model from the labeled source domain for the unlabeled target domain. Since the data distributions of the two domains are different, the model often performs poorly on the target…
Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…
In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical…
Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant…
This paper introduces a privacy-aware Bayesian approach that combines ensembles of classifiers and clusterers to perform semi-supervised and transductive learning. We consider scenarios where instances and their classification/clustering…
Unsupervised Domain Adaptation (UDA) methods for person Re-Identification (Re-ID) rely on target domain samples to model the marginal distribution of the data. To deal with the lack of target domain labels, UDA methods leverage information…
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that…
Recently unsupervised person re-identification (re-ID) has drawn much attention due to its open-world scenario settings where limited annotated data is available. Existing supervised methods often fail to generalize well on unseen domains,…
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms. However, such clustering-based scheme becomes…
Clustering problems (such as $k$-means and $k$-median) are fundamental unsupervised machine learning primitives, and streaming clustering algorithms have been extensively studied in the past. However, since data privacy becomes a central…
Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…
Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain. Beyond the traditional scope of UDA with a single source domain and a single target…
In this work, we consider the problem of cross-domain 3D action recognition in the open-set setting, which has been rarely explored before. Specifically, there is a source domain and a target domain that contain the skeleton sequences with…
Problem statement: Clustering has a number of techniques that have been developed in statistics, pattern recognition, data mining, and other fields. Subspace clustering enumerates clusters of objects in all subspaces of a dataset. It tends…
Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider…
Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift between the distribution of unlabeled data from the target domain w.r.t. labeled data from the source domain. While the single-target UDA scenario is well…
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it…
Existing Source-free Unsupervised Domain Adaptation (SUDA) approaches inherently exhibit catastrophic forgetting. Typically, models trained on a labeled source domain and adapted to unlabeled target data improve performance on the target…