Related papers: Learning to Generate Training Datasets for Robust …

The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates the vulnerabilities of current AI-generated face detection…

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive,…

Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this…

Real-time semantic segmentation of remote sensing imagery is a challenging task that requires a trade-off between effectiveness and efficiency. It has many applications including tracking forest fires, detecting changes in land use and land…

In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where…

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…

Semantic segmentation of remote sensing (RS) images is a challenging yet essential task with broad applications. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field,…

We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational…

Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex…

Computer vision tasks such as semantic segmentation perform very well in good weather conditions, but if the weather turns bad, they have problems to achieve this performance in these conditions. One possibility to obtain more robust and…

The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks with even lower labeling budgets, unlike prior approaches…

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…

Automated medical image analysis has a significant value in diagnosis and treatment of lesions. Brain tumors segmentation has a special importance and difficulty due to the difference in appearances and shapes of the different tumor regions…

In order to achieve good performance and generalisability, medical image segmentation models should be trained on sizeable datasets with sufficient variability. Due to ethics and governance restrictions, and the costs associated with…

Robust semantic segmentation under adverse conditions is crucial in real-world applications. To address this challenging task in practical scenarios where labeled normal condition images are not accessible in training, we propose FREST, a…

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…

Deep learning-based computer-aided diagnosis is gradually deployed to review and analyze medical images. However, this paradigm is restricted in real-world clinical applications due to the poor robustness and generalization. The issue is…

Semantic image synthesis (SIS) is a task to generate realistic images corresponding to semantic maps (labels). However, in real-world applications, SIS often encounters noisy user inputs. To address this, we propose Stochastic Conditional…

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image…

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…