Related papers: Self-Training and Adversarial Background Regulariz…

Self-training is an important class of unsupervised domain adaptation (UDA) approaches that are used to mitigate the problem of domain shift, when applying knowledge learned from a labeled source domain to unlabeled and heterogeneous target…

Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on their needs via a few labeled examples and minimal domain…

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Addressing performance degradation in 3D LiDAR semantic segmentation due to domain shifts (e.g., sensor type, geographical location) is crucial for autonomous systems, yet manual annotation of target data is prohibitive. This study…

In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the…

Recently, remarkable progress has been made in learning transferable representation across domains. Previous works in domain adaptation are majorly based on two techniques: domain-adversarial learning and self-training. However,…

Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels…

Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes. However, they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A…

Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain). Mean-teacher self-training is a powerful paradigm in unsupervised domain adaptation for object detection, but it…

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. However, pseudo-labeling-based semi-supervised approaches suffer from two problems in image classification: (1) Existing methods…

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…

Semi-supervised Fine-Grained Recognition is a challenge task due to the difficulty of data imbalance, high inter-class similarity and domain mismatch. Recent years, this field has witnessed great progress and many methods has gained great…

In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discriminative feature…

Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption…

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…

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…

Domain Adaptation methodologies have shown to effectively generalize from a labeled source domain to a label scarce target domain. Previous research has either focused on unlabeled domain adaptation without any target supervision or…