Related papers: GenMix: Combining Generative and Mixture Data Augm…

A generative modeling framework is proposed that combines diffusion models and manifold learning to efficiently sample data densities on manifolds. The approach utilizes Diffusion Maps to uncover possible low-dimensional underlying (latent)…

Availability of large amount of annotated data is one of the pillars of deep learning success. Although numerous big datasets have been made available for research, this is often not the case in real life applications (e.g. companies are…

Vision-Language Pre-training (VLP) is drawing increasing interest for its ability to minimize manual annotation requirements while enhancing semantic understanding in downstream tasks. However, its reliance on image-text datasets poses…

Brain lesion segmentation provides a valuable tool for clinical diagnosis, and convolutional neural networks (CNNs) have achieved unprecedented success in the task. Data augmentation is a widely used strategy that improves the training of…

In the field of computational pathology, deep learning algorithms have made significant progress in tasks such as nuclei segmentation and classification. However, the potential of these advanced methods is limited by the lack of available…

A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine…

Recent advances in synthetic imaging open up opportunities for obtaining additional data in the field of surgical imaging. This data can provide reliable supplements supporting surgical applications and decision-making through computer…

With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works show that it can effectively augment or even replace real data.…

Data scarcity in medical imaging poses significant challenges due to privacy concerns. Diffusion models, a recent generative modeling technique, offer a potential solution by generating synthetic and realistic data. However, questions…

Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…

User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven model compression faces a higher risk of performance degradation. Recently, some…

Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…

This paper studies stable learning methods for generative models that enable high-quality data generation. Noise injection is commonly used to stabilize learning. However, selecting a suitable noise distribution is challenging.…

The rapid advancement of generative models, such as Stable Diffusion, raises a key question: how can synthetic data from these models enhance predictive modeling? While they can generate vast amounts of datasets, only a subset meaningfully…

While learned image compression (LIC) focuses on efficient data transmission, generative image compression (GIC) extends this framework by integrating generative modeling to produce photo-realistic reconstructed images. In this paper, we…

Bioimage classification plays a crucial role in many biological problems. In this work, we present a new General Purpose (GenP) ensemble that boosts performance by combining local features, dense sampling features, and deep learning…

The fact that image datasets are often imbalanced poses an intense challenge for deep learning techniques. In this paper, we propose a method to restore the balance in imbalanced images, by coalescing two concurrent methods, generative…

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER)…

Unified multimodal generative models aim to integrate image understanding and generation abilities, offering significant advantages in harnessing multimodal corpora, particularly interleaved text-image data. However, existing unified models…

Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited…