Related papers: Image Counterfactual Sensitivity Analysis for Dete…

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing…

The use of counterfactuals for considerations of algorithmic fairness and explainability is gaining prominence within the machine learning community and industry. This paper argues for more caution with the use of counterfactuals when the…

The ability of humans to detect and respond to others' emotions is fundamental to understanding social behavior. Here, agents are instantiated with emotion classifiers of varying accuracy to study the impact of perceptual accuracy on…

As deep learning models are increasingly used in safety-critical applications, explainability and trustworthiness become major concerns. For simple images, such as low-resolution face portraits, synthesizing visual counterfactual…

In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility.…

State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to identifying faces. However, the implicit encoding of gender…

The growing incidents of counterfeiting and associated economic and health consequences necessitate the development of active surveillance systems capable of producing timely and reliable information for all stake holders in the…

In this paper, we demonstrate the feasibility of alterfactual explanations for black box image classifiers. Traditional explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial…

As the expressive depth of an emotional face differs with individuals or expressions, recognizing an expression using a single facial image at a moment is difficult. A relative expression of a query face compared to a reference face might…

Deep neural networks have proved hugely successful, achieving human-like performance on a variety of tasks. However, they are also computationally expensive, which has motivated the development of model compression techniques which reduce…

Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image.…

Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to…

In this work, we explore the features that are used by humans and by convolutional neural networks (ConvNets) to classify faces. We use Guided Backpropagation (GB) to visualize the facial features that influence the output of a ConvNet the…

Published research highlights the presence of demographic bias in automated facial attribute classification algorithms, particularly impacting women and individuals with darker skin tones. Existing bias mitigation techniques typically…

Recent developments in computer vision and machine learning have made it possible to create realistic manipulated videos of human faces, raising the issue of ensuring adequate protection against the malevolent effects unlocked by such…

The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation using StyleGAN2.…

Leveraging StyleGAN's expressivity and its disentangled latent codes, existing methods can achieve realistic editing of different visual attributes such as age and gender of facial images. An intriguing yet challenging problem arises: Can…

Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images. Previous works…

We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To this end, we…

Previous studies have shown that faces are rated as more attractive when they are partially occluded. The cause of this observation remains unclear. One explanation is a mental reconstruction of the occluded face parts which is biased…