Related papers: DIAGen: Semantically Diverse Image Augmentation wi…

Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data…

Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output…

Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However…

Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…

Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or…

Augmentation by generative modelling yields a promising alternative to the accumulation of surgical data, where ethical, organisational and regulatory aspects must be considered. Yet, the joint synthesis of (image, mask) pairs for…

Diffusion models enable high-quality and diverse visual content synthesis. However, they struggle to generate rare or unseen concepts. To address this challenge, we explore the usage of Retrieval-Augmented Generation (RAG) with image…

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful…

While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that augments diffusion…

Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative…

Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To…

In biomedical engineering, artificial intelligence has become a pivotal tool for enhancing medical diagnostics, particularly in medical image classification tasks such as detecting pneumonia from chest X-rays and breast cancer screening.…

In this paper, we present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) to tackle the challenges inherent in data-scarce scenarios. Recently, DMs have opened up the possibility…

Surface electromyography (sEMG)-based gesture recognition plays a critical role in human-machine interaction (HMI), particularly for rehabilitation and prosthetic control. However, sEMG-based systems often suffer from the scarcity of…

Current child face generators are restricted by the limited size of the available datasets. In addition, feature selection can prove to be a significant challenge, especially due to the large amount of features that need to be trained for.…

Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the…

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…

Text classification is a representative downstream task of natural language processing, and has exhibited excellent performance since the advent of pre-trained language models based on Transformer architecture. However, in pre-trained…

Medical image data is less accessible than in other domains due to privacy and regulatory constraints. In addition, labeling requires costly, time-intensive manual image annotation by clinical experts. To overcome these challenges,…