Learning scale-variant and scale-invariant features for deep image classification
نویسندگان
چکیده
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 scaleinvariant and scale-variant representations. We propose a multiscale 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.
منابع مشابه
DPML-Risk: An Efficient Algorithm for Image Registration
Targets and objects registration and tracking in a sequence of images play an important role in various areas. One of the methods in image registration is feature-based algorithm which is accomplished in two steps. The first step includes finding features of sensed and reference images. In this step, a scale space is used to reduce the sensitivity of detected features to the scale changes. Afterw...
متن کاملPorosity classification from thin sections using image analysis and neural networks including shallow and deep learning in Jahrum formation
The porosity within a reservoir rock is a basic parameter for the reservoir characterization. The present paper introduces two intelligent models for identification of the porosity types using image analysis. For this aim, firstly, thirteen geometrical parameters of pores of each image were extracted using the image analysis techniques. The extracted features and their corresponding pore types ...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملMulti-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation
Large-scale image annotation is a challenging task in image content analysis, which aims to annotate each image of a very large dataset with multiple class labels. In this paper, we focus on two main issues in large-scale image annotation: 1) how to learn stronger features for multifarious images; 2) how to annotate an image with an automatically-determined number of class labels. To address th...
متن کاملClassification of Brain Tumor by Combination of Pre-Trained VGG16 CNN
In recent years, brain tumors become the leading cause of death in the world. Detection and rapid classification of this tumor are very important and may indicate the likely diagnosis and treatment strategy. In this paper, we propose deep learning techniques based on the combinations of pre-trained VGG-16 CNNs to classify three types of brain tumors (i.e., meningioma, glioma, and pituitary tumo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Pattern Recognition
دوره 61 شماره
صفحات -
تاریخ انتشار 2017