In this paper, we develop a 16-layer, yet lightweight, neural network which boosts efficiency while maintaining high accuracy. Our net is pruned from the VGG-16 ...

Many real-time tasks, such as human-computer interac- tion, require fast and efficient facial gender classification. Although deep CNN nets have been very ...

Jul 21, 2017 · Demonstration of pruning on filter level (cyan indicates remaining data, green represents the surviving part of a remaining next layer filter).

In this paper, we develop a 16-layer, yet lightweight, neural network which boosts efficiency while maintaining high accuracy. Our net is pruned from the VGG-16 ...

Combined with either Support Vector Machines (SVM) or Bayesian classification, the reduced CNNs are capable of achieving comparable (or even higher) accuracies ...

Efficient Gender Classification Using a Deep LDA-Pruned Net​​ Many real-time tasks, such as human-computer interaction, require fast and efficient facial gender ...

In this paper, we propose a structured filter-level pruning approach based on Fisher LDA [1], which boosts efficiency while maintaining accuracy for facial ...

A neuron/filter level pruning framework based on Fisher's LDA which leads to high accuracies for a wide array of facial trait classification tasks.

In this paper, we address this problem by introducing a task-dependent deep pruning framework based on Fisher's Linear Discriminant Analysis (LDA).

Apr 4, 2020 · Deep lda-pruned nets for efficient facial gender classification. In ... Structured deep fisher pruning for efficient facial trait classifi- cation ...