Related papers: Adaptive Spatial Augmentation for Semi-supervised …

Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques…

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…

In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classified with high…

Semantic segmentation is a critical step in automated image interpretation and analysis where pixels are classified into one or more predefined semantically meaningful classes. Deep learning approaches for semantic segmentation rely on…

Deep learning enabled semantic communications are attracting extensive attention. However, most works normally ignore the data acquisition process and suffer from robustness issues under dynamic channel environment. In this paper, we…

Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…

Recent state-of-the-art semi-supervised learning (SSL) methods use a combination of image-based transformations and consistency regularization as core components. Such methods, however, are limited to simple transformations such as…

State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction…

Robustness and generalizability in medical image segmentation are often hindered by scarcity and limited diversity of training data, which stands in contrast to the variability encountered during inference. While conventional strategies --…

Strong data augmentation is a fundamental component of state-of-the-art mean teacher-based Source-Free domain adaptive Object Detection (SFOD) methods, enabling consistency-based self-supervised optimization along weak augmentation.…

In this paper, we investigate the problem of Semantic Segmentation for agricultural aerial imagery. We observe that the existing methods used for this task are designed without considering two characteristics of the aerial data: (i) the…

Convolutional neural networks have been widely applied to medical image segmentation and have achieved considerable performance. However, the performance may be significantly affected by the domain gap between training data (source domain)…

Learning segmentation from synthetic data and adapting to real data can significantly relieve human efforts in labelling pixel-level masks. A key challenge of this task is how to alleviate the data distribution discrepancy between the…

High spatial frequency information, including fine details like textures, significantly contributes to the accuracy of semantic segmentation. However, according to the Nyquist-Shannon Sampling Theorem, high-frequency components are…

Data augmentation is widely used as a part of the training process applied to deep learning models, especially in the computer vision domain. Currently, common data augmentation techniques are designed manually. Therefore they require…

Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it always focuses on the most discriminative regions, resulting in…

Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when applied to unseen…

Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by…

Data augmentation is a widely used and effective technique to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability when working with medical images, it is frequently…

Data augmentation is a central component of joint embedding self-supervised learning (SSL). Approaches that work for natural images may not always be effective in medical imaging tasks. This study systematically investigated the impact of…