Related papers: Source-Free Cross-Domain Continual Learning

Domain adaptation is often hampered by exceedingly small target datasets and inaccessible source data. These conditions are prevalent in speech verification, where privacy policies and/or languages with scarce speech resources limit the…

Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.…

Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source model may represent a solution for the first but does not…

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…

In recent years, defect prediction techniques based on deep learning have become a prominent research topic in the field of software engineering. These techniques can identify potential defects without executing the code. However, existing…

We aim for source-free domain adaptation, where the task is to deploy a model pre-trained on source domains to target domains. The challenges stem from the distribution shift from the source to the target domain, coupled with the…

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing…

Semi-Supervised Domain Adaptation (SSDA) involves learning to classify unseen target data with a few labeled and lots of unlabeled target data, along with many labeled source data from a related domain. Current SSDA approaches usually aim…

Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions. However, as any data scientist…

Source-free domain adaptation (SFDA) utilizes a pre-trained source model with unlabeled target data. Self-supervised SFDA techniques generate pseudolabels from the pre-trained source model, but these pseudolabels often contain noise due to…

In practice, domain shifts are likely to occur between training and test data, necessitating domain adaptation (DA) to adjust the pre-trained source model to the target domain. Recently, universal domain adaptation (UniDA) has gained…

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…

Existing SFDA methods struggle to fully use pre-trained knowledge and often rely on a single model's predictions or handcrafted prompts, limiting robustness under domain shift. Multimodal Large Language Models (MLLMs) offer a promising…

Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…

Generalising deep networks to novel domains without manual labels is challenging to deep learning. This problem is intrinsically difficult due to unpredictable changing nature of imagery data distributions in novel domains. Pre-learned…

Current supervised cross-domain image retrieval methods can achieve excellent performance. However, the cost of data collection and labeling imposes an intractable barrier to practical deployment in real applications. In this paper, we…

As the volume of data continues to expand, it becomes increasingly common for data to be aggregated from multiple sources. Leveraging multiple sources for model training typically achieves better predictive performance on test datasets.…

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…