Related papers: Enhancing Image Classification in Small and Unbala…

Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical…

Supervised deep learning methods are enjoying enormous success in many practical applications of computer vision and have the potential to revolutionize robotics. However, the marked performance degradation to biases and imbalanced data…

Weakly-supervised image segmentation (WSIS) is a critical task in computer vision that relies on image-level class labels. Multi-stage training procedures have been widely used in existing WSIS approaches to obtain high-quality pseudo-masks…

Convolutional Neural Networks (CNNs) serve as the workhorse of deep learning, finding applications in various fields that rely on images. Given sufficient data, they exhibit the capacity to learn a wide range of concepts across diverse…

Skin cancer is one of the most common cancers worldwide and early detection is critical for effective treatment. However, current AI diagnostic tools are often trained on datasets dominated by lighter skin tones, leading to reduced accuracy…

Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into…

Machine learning models trained on imbalanced datasets often exhibit intersectional biases-systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a…

The amount of image datasets collected for environmental monitoring purposes has increased in the past years as computer vision assisted methods have gained interest. Computer vision applications rely on high-quality datasets, making data…

In this research, we introduce an innovative method for synthesizing medical images using generative adversarial networks (GANs). Our proposed GANs method demonstrates the capability to produce realistic synthetic images even when trained…

This work addresses how to efficiently classify challenging histopathology images, such as gigapixel whole-slide images for cancer diagnostics with image-level annotation. We use images with annotated tumor regions to identify a set of…

High-resolution medical images are beneficial for analysis but their acquisition may not always be feasible. Alternatively, high-resolution images can be created from low-resolution acquisitions using conventional upsampling methods, but…

In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and…

In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related…

Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using…

While medical image segmentation is an important task for computer aided diagnosis, the high expertise requirement for pixelwise manual annotations makes it a challenging and time consuming task. Since conventional data augmentations do not…

For classifying digital whole slide images in the absence of pixel level annotation, typically multiple instance learning methods are applied. Due to the generic applicability, such methods are currently of very high interest in the…

Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical factor that affects on the generalization ability of image…

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Limited data availability in machine learning significantly impacts performance and generalization. Traditional augmentation methods enhance moderately sufficient datasets. GANs struggle with convergence when generating diverse samples.…