4 papers
Sparse Competition during Training For the Emergence of Specialized Modules
Baptiste Rossigneux, Karim Haroun
Modularity in deep neural networks has been proposed as a means of improving both interpretability and training by promoting disentangled representations and reducing redundancy. I…
Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction
Aya Manel Zitouni, Aicha Zenakhri, Karim Haroun +1
Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-computer interaction. Current Vi…
Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AI
Karim Haroun, Aya Zitouni, Aicha Zenakhri +2
Recent advances in deep learning, whether on discriminative or generative tasks have been beneficial for various applications, among which security and defense. However, their incr…
Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers
Lucas Maisonnave, Karim Haroun, Tom Pegeot
Transformer models rely on Multi-Head Self-Attention (MHSA) mechanisms, where each attention head contributes to the final representation. However, their computational complexity a…