Deep Mean Maps

11/13/2015
by   Junier B. Oliva, et al.
0

The use of distributions and high-level features from deep architecture has become commonplace in modern computer vision. Both of these methodologies have separately achieved a great deal of success in many computer vision tasks. However, there has been little work attempting to leverage the power of these to methodologies jointly. To this end, this paper presents the Deep Mean Maps (DMMs) framework, a novel family of methods to non-parametrically represent distributions of features in convolutional neural network models. DMMs are able to both classify images using the distribution of top-level features, and to tune the top-level features for performing this task. We show how to implement DMMs using a special mean map layer composed of typical CNN operations, making both forward and backward propagation simple. We illustrate the efficacy of DMMs at analyzing distributional patterns in image data in a synthetic data experiment. We also show that we extending existing deep architectures with DMMs improves the performance of existing CNNs on several challenging real-world datasets.

READ FULL TEXT

page 5

page 6

page 7

research
11/15/2018

Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector

Different layers of deep convolutional neural networks(CNN) can encode d...
research
05/24/2019

Not All Features Are Equal: Feature Leveling Deep Neural Networks for Better Interpretation

Self-explaining models are models that reveal decision making parameters...
research
01/29/2015

On Vectorization of Deep Convolutional Neural Networks for Vision Tasks

We recently have witnessed many ground-breaking results in machine learn...
research
08/17/2020

An Improved Dilated Convolutional Network for Herd Counting in Crowded Scenes

Crowd management technologies that leverage computer vision are widespre...
research
12/31/2018

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks

One of the ultimate promises of computer vision is to help robotic agent...
research
06/19/2018

Multimodal feature fusion for CNN-based gait recognition: an empirical comparison

People identification in video based on the way they walk (i.e. gait) is...
research
09/29/2020

MARA-Net: Single Image Deraining Network with Multi-level connections and Adaptive Regional Attentions

Removing rain streaks from single images is an important problem in vari...

Please sign up or login with your details

Forgot password? Click here to reset