MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images

11/19/2017
by   İlke Çuğu, et al.
0

This paper is aimed at creating extremely small and fast convolutional neural networks (CNN) for the problem of facial expression recognition (FER) from frontal face images. We show that, for this problem, translation invariance (achieved through max-pooling layers) degrades performance, especially when the network is small, and that the knowledge distillation method can be used to obtain extremely compressed CNNs. Extensive comparisons on two widely-used FER datasets, CK+ and Oulu-CASIA, demonstrate that our largest model sets the new state-of-the-art by yielding 1.8 previous best results, on CK+ and Oulu-CASIA datasets, respectively. In addition, our smallest model (MicroExpNet), obtained using knowledge distillation, is less than 1MB in size and works at 1408 frames per second on an Intel i7 CPU. Being slightly less accurate than our largest model, MicroExpNet still achieves a 8.3 dataset, over the previous state-of-the-art, much larger network; and on the CK+ dataset, it performs on par with a previous state-of-the-art network but with 154x fewer parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/21/2023

Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection

Facial forgery detection is a crucial but extremely challenging topic, w...
research
08/24/2021

PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation

Deep neural networks have rapidly become the mainstream method for face ...
research
05/17/2019

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis

Cross-domain synthesizing realistic faces to learn deep models has attra...
research
03/08/2023

Enhancing Low-resolution Face Recognition with Feature Similarity Knowledge Distillation

In this study, we introduce a feature knowledge distillation framework t...
research
02/27/2018

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

We propose a network for Congested Scene Recognition called CSRNet to pr...
research
08/20/2021

Knowledge Distillation from Ensemble of Offsets for Head Pose Estimation

This paper proposes a method for estimating the head pose from a single ...
research
12/01/2016

In Teacher We Trust: Learning Compressed Models for Pedestrian Detection

Deep convolutional neural networks continue to advance the state-of-the-...

Please sign up or login with your details

Forgot password? Click here to reset