Multilevel Context Representation for Improving Object Recognition

In this work, we propose the combined usage of low- and high-level blocks of convolutional neural networks (CNNs) for improving object recognition. While recent research focused on either propagating the context from all layers, e.g. ResNet, (including the very low-level layers) or having multiple loss layers (e.g. GoogLeNet), the importance of the features close to the higher layers is ignored. This paper postulates that the use of context closer to the high-level layers provides the scale and translation invariance and works better than using the top layer only. In particular, we extend AlexNet and GoogLeNet by additional connections in the top n layers. In order to demonstrate the effectiveness of the proposed approach, we evaluated it on the standard ImageNet task. The relative reduction of the classification error is around 1-2% without affecting the computational cost. Furthermore, we show that this approach is orthogonal to typical test data augmentation techniques, as recently introduced by Szegedy et al. (leading to a runtime reduction of 144 during test time).

Project Details

Date: Mar 19, 2017

Author: Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki

Categories: projectobject recognitioncontext representation


Related Works.

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network

Multilevel Context Representation for Improving Object Recognition

Music Information Retrieval

Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection


We believe that creativity comes with freedom and to solve challenging problems in AI we need to have freedom and creative thinking. We provide an unconstrained environment to highly motivated students to do whatever that comes to their minds and explore deep learning.

Social Links

Our Bunker

Rooms 36-(307/309/310),
TU Kaiserslautern,
Paul-Ehrlich-Str. 36,
67663 Kaiserslautern,