Related papers: Self-Supervised Visual Prompting for Cross-Domain …

Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on…

Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the…

Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set for hyper-parameter tuning and model selection. In this…

Video semantic segmentation has achieved great progress under the supervision of large amounts of labelled training data. However, domain adaptive video segmentation, which can mitigate data labelling constraints by adapting from a labelled…

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a different but related fully-unlabeled target domain. To address the problem of domain shift, more and more UDA methods adopt pseudo labels of the…

Understanding foggy image sequence in the driving scenes is critical for autonomous driving, but it remains a challenging task due to the difficulty in collecting and annotating real-world images of adverse weather. Recently, the…

In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

Source-free domain-adaptive object detection is an interesting but scarcely addressed topic. It aims at adapting a source-pretrained detector to a distinct target domain without resorting to source data during adaptation. So far, there is…

We propose a novel framework for enhancing robotic adaptability and learning efficiency, which integrates unsupervised trajectory segmentation with adaptive probabilistic movement primitives (ProMPs). By employing a cutting-edge deep…

Surface defect detection is a critical task across numerous industries, aimed at efficiently identifying and localising imperfections or irregularities on manufactured components. While numerous methods have been proposed, many fail to meet…

Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data…

Prompt-conditioned foundation segmenters have emerged as a dominant paradigm for image segmentation, where explicit spatial prompts (e.g., points, boxes, masks) guide mask decoding. However, many real-world deployments require fully…

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of…

Unsupervised instance segmentation aims to segment distinct object instances in an image without relying on human-labeled data. This field has recently seen significant advancements, partly due to the strong local correspondences afforded…

This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT). By freezing the SSVT backbone and training a lightweight segmentation head, our approach effectively utilizes…

Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. In the realm of computer vision, pretrained vision transformers…

Most research on domain adaptation has focused on the purely unsupervised setting, where no labeled examples in the target domain are available. However, in many real-world scenarios, a small amount of labeled target data is available and…