Related papers: Dual form Complementary Masking for Domain-Adaptiv…

Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentations, primarily due to unstable training. In this paper, we…

Pre-trained diffusion models have demonstrated remarkable proficiency in synthesizing images across a wide range of scenarios with customizable prompts, indicating their effective capacity to capture universal features. Motivated by this,…

Recently, learning-based algorithms have shown impressive performance in underwater image enhancement. Most of them resort to training on synthetic data and achieve outstanding performance. However, these methods ignore the significant…

Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including…

Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…

As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods…

Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D point cloud data and mitigating the absence of labels when facing a newly defined domain. Various methods of utilizing images to enhance the…

Person Re-Identification (ReID) across non-overlapping cameras is a challenging task and, for this reason, most works in the prior art rely on supervised feature learning from a labeled dataset to match the same person in different views.…

Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. The…

This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling…

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…

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models that predict the…

Unsupervised domain adaptation (UDA) between two significantly disparate domains to learn high-level semantic alignment is a crucial yet challenging task.~To this end, in this work, we propose exploiting low-level edge information to…

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate…

Unsupervised anomaly segmentation approaches to pathology segmentation train a model on images of healthy subjects, that they define as the 'normal' data distribution. At inference, they aim to segment any pathologies in new images as…

This paper addresses the task of cross-modal medical image segmentation by exploring unsupervised domain adaptation (UDA) approaches. We propose a model-agnostic UDA framework, LowBridge, which builds on a simple observation that…

The insertion of deep learning in medical image analysis had lead to the development of state-of-the art strategies in several applications such a disease classification, as well as abnormality detection and segmentation. However, even the…

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other. The proposed method disentangles the common and separate parts of these domains…

Training of semantic segmentation models for material analysis requires micrographs and their corresponding masks. It is quite unlikely that perfect masks will be drawn, especially at the edges of objects, and sometimes the amount of data…

Existing rotation-invariant point cloud masked autoencoders (MAE) rely on random masking strategies that overlook geometric structure and semantic coherence. Random masking treats patches independently, failing to capture spatial…