ML p(r)ior | Learning scale-variant and scale-invariant features for deep image classification

Learning scale-variant and scale-invariant features for deep image classification

2016-02-03
1602.01255 | cs.CV
Convolutional Neural Networks (CNNs) require large image corpora to be trained on classification tasks. The variation in image resolutions, sizes of objects and patterns depicted, and image scales, hampers CNN training and performance, because the task-relevant information varies over spatial scales. Previous work attempting to deal with such scale variations focused on encouraging scale-invariant CNN representations. However, scale-invariant representations are incomplete representations of images, because images contain scale-variant information as well. This paper addresses the combined development of scale-invariant and scale-variant representations. We propose a multi- scale CNN method to encourage the recognition of both types of features and evaluate it on a challenging image classification task involving task-relevant characteristics at multiple scales. The results show that our multi-scale CNN outperforms single-scale CNN. This leads to the conclusion that encouraging the combined development of a scale-invariant and scale-variant representation in CNNs is beneficial to image recognition performance.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2016-12-13
1612.04402 | cs.CV

Though tremendous strides have been made in object recognition, one of the remaining open challenges… show more
PDF

Highlights - Most important sentences from the article

2018-04-11

We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus … show more
PDF

Highlights - Most important sentences from the article

2015-11-14
1511.04587 | cs.CV

We present a highly accurate single-image super-resolution (SR) method. Our method uses a very deep … show more
PDF

Highlights - Most important sentences from the article

2019-04-02

Representing features at multiple scales is of great importance for numerous vision tasks. Recent ad… show more
PDF

Highlights - Most important sentences from the article

2014-06-18

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224x224) input image.… show more
PDF

Highlights - Most important sentences from the article

2017-11-03

Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant … show more
PDF

Highlights - Most important sentences from the article

2013-12-21

We present an integrated framework for using Convolutional Networks for classification, localization… show more
PDF

Highlights - Most important sentences from the article

2016-10-04

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially d… show more
PDF

Highlights - Most important sentences from the article

2016-11-19
1611.06430 | cs.CV

We introduce a simple semi-supervised learning approach for images based on in-painting using an adv… show more
PDF

Highlights - Most important sentences from the article

2018-05-23

We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visu… show more
PDF

Highlights - Most important sentences from the article

2017-07-22
1707.07128 | cs.CV

Traditional works have shown that patches in a natural image tend to redundantly recur many times in… show more
PDF

Highlights - Most important sentences from the article

2017-07-29

Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variation… show more
PDF

Highlights - Most important sentences from the article

2017-10-11

Standing at the paradigm shift towards data-intensive science, machine learning techniques are becom… show more
PDF

Highlights - Most important sentences from the article

2019-02-18

Predicting salient regions in natural images requires the detection of objects that are present in a… show more
PDF

Highlights - Most important sentences from the article

2016-04-01
1604.00187 | cs.CV

In recent years, deep convolutional neural networks have achieved state of the art performance in va… show more
PDF

Highlights - Most important sentences from the article

2019-05-02

As an instance-level recognition problem, person re-identification (ReID) relies on discriminative f… show more
PDF