相关论文: Compressed Models Decompress Race Biases: What Qua…

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…

Face parsing is a fundamental task in computer vision, enabling applications such as identity verification, facial editing, and controllable image synthesis. However, existing face parsing models often lack fairness and robustness, leading…

No single classifier can alone solve the complex problem of face recognition. Researchers found that combining some base classifiers usually enhances their recognition rate. The weaknesses of the base classifiers are reflected on the…

Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. However, to enable a trustworthy FR…

Quantization lowers memory usage, computational requirements, and latency by utilizing fewer bits to represent model weights and activations. In this work, we investigate the generalization properties of quantized neural networks, a…

Ensuring that AI-based facial recognition systems produce fair predictions and work equally well across all demographic groups is crucial. Earlier systems often exhibited demographic bias, particularly in gender and racial classification,…

Despite the success of deep-learning models in many tasks, there have been concerns about such models learning shortcuts, and their lack of robustness to irrelevant confounders. When it comes to models directly trained on human faces, a…

Bias is known to be an impediment to fair decisions in many domains such as human resources, the public sector, health care etc. Recently, hope has been expressed that the use of machine learning methods for taking such decisions would…

Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often…

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…

In recent years, the rapid development of artificial intelligence (AI) systems has raised concerns about our ability to ensure their fairness, that is, how to avoid discrimination based on protected characteristics such as gender, race, or…

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks…

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce…

The digitalization of credit scoring has become essential for financial institutions and commercial banks, especially in the era of digital transformation. Machine learning techniques are commonly used to evaluate customers'…

Deep neural networks are the state-of-the-art methods for many real-world tasks, such as computer vision, natural language processing and speech recognition. For all its popularity, deep neural networks are also criticized for consuming a…

Fairness has been a critical issue that affects the adoption of deep learning models in real practice. To improve model fairness, many existing methods have been proposed and evaluated to be effective in their own contexts. However, there…

Robots and artificial agents that interact with humans should be able to do so without bias and inequity, but facial perception systems have notoriously been found to work more poorly for certain groups of people than others. In our work,…

The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of…

Imbalanced data, where the positive samples represent only a small proportion compared to the negative samples, makes it challenging for classification problems to balance the false positive and false negative rates. A common approach to…