Related papers: Discover and Mitigate Multiple Biased Subgroups in…

Despite the remarkable success of diffusion models (DMs) in data generation, they exhibit specific failure cases with unsatisfactory outputs. We focus on one such limitation: the ability of DMs to learn hidden rules between image features.…

Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data…

Scientific literature contains large volumes of complex, unstructured figures that are compound in nature (i.e. composed of multiple images, graphs, and drawings). Separation of these compound figures is critical for information retrieval…

Artificial Intelligence (AI)-powered pathology is a revolutionary step in the world of digital pathology and shows great promise to increase both diagnosis accuracy and efficiency. However, defocus and motion blur can obscure tissue or cell…

Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albedo…

In semantic segmentation datasets, classes of high importance are oftentimes underrepresented, e.g., humans in street scenes. Neural networks are usually trained to reduce the overall number of errors, attaching identical loss to errors of…

Moire artifacts are common in digital photography, resulting from the interference between high-frequency scene content and the color filter array of the camera. Existing deep learning-based demoireing methods trained on large scale…

Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that…

When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms. In…

The development of mobile and on the edge applications that embed deep convolutional neural models has the potential to revolutionise biomedicine. However, most deep learning models require computational resources that are not available in…

In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise…

Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the…

Blind image separation (BIS) refers to the inverse problem of simultaneously estimating and restoring multiple independent source images from a single observation image under conditions of unknown mixing mode and without prior knowledge of…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion…

Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing computational demands of modern deep learning. Recently,…

Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the scaling capability of masked image modeling (MIM) methods…

Masked image modelling (MIM) is a powerful self-supervised representation learning paradigm, whose potential has not been widely demonstrated in medical image analysis. In this work, we show the capacity of MIM to capture rich semantic…

A significant number of researchers have applied deep learning methods to image fusion. However, most works require a large amount of training data or depend on pre-trained models or frameworks to capture features from source images. This…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…