Logo des Repositoriums

Auflistung nach Schlagwort "Computational efficiency in biometrics"

1 - 2 von 2
  • Konferenzbeitrag
    Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition
    (BIOSIG 2023, 2023) Pedro C. Neto, Eduarda Caldeira
    With the ever-growing complexity of deep learning models for face recognition, it becomes hard to deploy these systems in real life. Researchers have two options: 1) use smaller models; 2) compress their current models. Since the usage of smaller models might lead to concerning biases, compression gains relevance. However, compressing might be also responsible for an increase in the bias of the final model. We investigate the overall performance, the performance on each ethnicity subgroup and the racial bias of a State-of-the-Art quantization approach when used with synthetic and real data. This analysis provides a few more details on potential benefits of performing quantization with synthetic data, for instance, the reduction of biases on the majority of test scenarios. We tested five distinct architectures and three different training datasets. The models were evaluated on a fourth dataset which was collected to infer and compare the performance of face recognition models on different ethnicity.
  • Konferenzbeitrag
    Exploiting Face Recognizability with Early Exit Vision Transformers
    (BIOSIG 2023, 2023) Seth Nixon, Pietro Ruiu
    Face recognition with Deep Learning is generally approached as a problem of capacity. The field has seen progressively deeper, more complex models or larger, more highly variant datasets. However, the carbon footprint of machine learning is a concern. A real push is developing to reduce the energy consumption of machine learning as we strive for a more eco-friendly society. Lower energy consumption or compute budget is always desirable, if accuracy is not reduced below a usable level. We present an approach using the state of the art Vision Transformer and Early Exits for reducing compute budget without significantly affecting performance. We develop a system for face recognition and identification with a closed-set gallery and show that with a small reduction in performance, a reasonable reduction in compute cost can be obtained using our method.