Learning Class Regularized Features for Action Recognition

02/07/2020
by   Alexandros Stergiou, et al.
0

Training Deep Convolutional Neural Networks (CNNs) is based on the notion of using multiple kernels and non-linearities in their subsequent activations to extract useful features. The kernels are used as general feature extractors without specific correspondence to the target class. As a result, the extracted features do not correspond to specific classes. Subtle differences between similar classes are modeled in the same way as large differences between dissimilar classes. To overcome the class-agnostic use of kernels in CNNs, we introduce a novel method named Class Regularization that performs class-based regularization of layer activations. We demonstrate that this not only improves feature search during training, but also allows an explicit assignment of features per class during each stage of the feature extraction process. We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1.8 1.4

READ FULL TEXT
research
03/22/2020

Ensembles of Deep Neural Networks for Action Recognition in Still Images

Despite the fact that notable improvements have been made recently in th...
research
10/05/2021

Efficient Modelling Across Time of Human Actions and Interactions

This thesis focuses on video understanding for human action and interact...
research
09/18/2019

Class Feature Pyramids for Video Explanation

Deep convolutional networks are widely used in video action recognition....
research
07/21/2017

Multi-kernel learning of deep convolutional features for action recognition

Image understanding using deep convolutional network has reached human-l...
research
01/29/2021

The Mind's Eye: Visualizing Class-Agnostic Features of CNNs

Visual interpretability of Convolutional Neural Networks (CNNs) has gain...
research
10/19/2020

ERIC: Extracting Relations Inferred from Convolutions

Our main contribution is to show that the behaviour of kernels across mu...
research
09/15/2023

P-ROCKET: Pruning Random Convolution Kernels for Time Series Classification

In recent years, two time series classification models, ROCKET and MINIR...

Please sign up or login with your details

Forgot password? Click here to reset