Saved in:
Bibliographic Details
Main Authors: Du, Chen, Wang, Chunheng, Wang, Yanna, Shi, Cunzhao, Xiao, Baihua
Format: Preprint
Published: 2018
Subjects:
Online Access:https://arxiv.org/abs/1811.06295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929604266033152
author Du, Chen
Wang, Chunheng
Wang, Yanna
Shi, Cunzhao
Xiao, Baihua
author_facet Du, Chen
Wang, Chunheng
Wang, Yanna
Shi, Cunzhao
Xiao, Baihua
contents Different layers of deep convolutional neural networks(CNNs) can encode different-level information. High-layer features always contain more semantic information, and low-layer features contain more detail information. However, low-layer features suffer from the background clutter and semantic ambiguity. During visual recognition, the feature combination of the low-layer and high-level features plays an important role in context modulation. If directly combining the high-layer and low-layer features, the background clutter and semantic ambiguity may be caused due to the introduction of detailed information. In this paper, we propose a general network architecture to concatenate CNN features of different layers in a simple and effective way, called Selective Feature Connection Mechanism (SFCM). Low-level features are selectively linked to high-level features with a feature selector which is generated by high-level features. The proposed connection mechanism can effectively overcome the above-mentioned drawbacks. We demonstrate the effectiveness, superiority, and universal applicability of this method on multiple challenging computer vision tasks, including image classification, scene text detection, and image-to-image translation.
format Preprint
id arxiv_https___arxiv_org_abs_1811_06295
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
Du, Chen
Wang, Chunheng
Wang, Yanna
Shi, Cunzhao
Xiao, Baihua
Computer Vision and Pattern Recognition
Different layers of deep convolutional neural networks(CNNs) can encode different-level information. High-layer features always contain more semantic information, and low-layer features contain more detail information. However, low-layer features suffer from the background clutter and semantic ambiguity. During visual recognition, the feature combination of the low-layer and high-level features plays an important role in context modulation. If directly combining the high-layer and low-layer features, the background clutter and semantic ambiguity may be caused due to the introduction of detailed information. In this paper, we propose a general network architecture to concatenate CNN features of different layers in a simple and effective way, called Selective Feature Connection Mechanism (SFCM). Low-level features are selectively linked to high-level features with a feature selector which is generated by high-level features. The proposed connection mechanism can effectively overcome the above-mentioned drawbacks. We demonstrate the effectiveness, superiority, and universal applicability of this method on multiple challenging computer vision tasks, including image classification, scene text detection, and image-to-image translation.
title Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1811.06295