相关论文: Better May Not Be Fairer: A Study on Subgroup Disc…

Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender. Accuracy on dark-skinned females is significantly worse than on…

The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines…

Synthetic image generation has opened up new opportunities but has also created threats in regard to privacy, authenticity, and security. Detecting fake images is of paramount importance to prevent illegal activities, and previous research…

Measuring the colorfulness of a natural or virtual scene is critical for many applications in image processing field ranging from capturing to display. In this paper, we propose the first deep learning-based colorfulness estimation metric.…

Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world…

Biometric recognition is used across a variety of applications from cyber security to border security. Recent research has focused on ensuring biometric performance (false negatives and false positives) is fair across demographic groups.…

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a…

Systematic mislabelling affecting specific subgroups (i.e., label bias) in medical imaging datasets represents an understudied issue concerning the fairness of medical AI systems. In this work, we investigated how size and separability of…

In this paper, we propose an image matting framework called Salient Image Matting to estimate the per-pixel opacity value of the most salient foreground in an image. To deal with a large amount of semantic diversity in images, a trimap is…

Recent advancements in image synthesis have enabled high-quality image generation and manipulation. Most works focus on: 1) conditional manipulation, where an image is modified conditioned on a given attribute, or 2) disentangled…

Image quality assessment often relies on raw opinion scores provided by subjects in subjective experiments, which can be noisy and unreliable. To address this issue, postprocessing procedures such as ITU-R BT.500, ITU-T P.910, and ITU-T…

Accurate representation in media is known to improve the well-being of the people who consume it. Generative image models trained on large web-crawled datasets such as LAION are known to produce images with harmful stereotypes and…

Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correlations, between input samples and the target labels, wrongly…

The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make…

Diffusion Models have demonstrated remarkable performance in image generation. However, their demanding computational requirements for training have prompted ongoing efforts to enhance the quality of generated images through modifications…

Facial expression recognition (FER) algorithms classify facial expressions into emotions such as happy, sad, or angry. An evaluative challenge facing FER algorithms is the fall in performance when detecting spontaneous expressions compared…

Contrastive Learning has shown impressive results on natural and medical images, without requiring annotated data. However, a particularity of medical images is the availability of meta-data (such as age or sex) that can be exploited for…

The contemporary state-of-the-art of Dynamic Facial Expression Recognition (DFER) technology facilitates remarkable progress by deriving emotional mappings of facial expressions from video content, underpinned by training on voluminous…

Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge. Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the…

In this study, we identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP (Contrastive…