PFFN

计算机科学 判别式 人工智能 特征(语言学) 块(置换群论) 利用 特征学习 架空(工程) 增采样 卷积神经网络 模式识别(心理学) 计算机工程 图像(数学) 操作系统 哲学 几何学 语言学 计算机安全 数学
作者
Dongyang Zhang,Changyu Li,Ning Xie,Guoqing Wang,Jie Shao
标识
DOI:10.1145/3474085.3475650
摘要

Recently, convolutional neural network (CNN) has been the core ingredient of modern models, triggering the surge of deep learning in super-resolution (SR). Despite the great success of these CNN-based methods which are prone to be deeper and heavier, it is impracticable to directly apply these methods for some low-budget devices due to the superfluous computational overhead. To alleviate this problem, a novel lightweight SR network named progressive feature fusion network (PFFN) is developed to seek for better balance between performance and running efficiency. Specifically, to fully exploit the feature maps, a novel progressive attention block (PAB) is proposed as the main building block of PFFN. The proposed PAB adopts several parallel but connected paths with pixel attention, which could significantly increase the receptive field of each layer, distill useful information and finally learn more discriminative feature representations. In PAB, a powerful dual attention module (DAM) is further incorporated to provide the channel and spatial attention mechanism in fairly lightweight manner. Besides, we construct a pretty concise and effective upsampling module with the help of multi-scale pixel attention, named MPAU. All of the above modules ensure the network can benefit from attention mechanism while still being lightweight enough. Furthermore, a novel training strategy following the cosine annealing learning scheme is proposed to maximize the representation ability of the model. Comprehensive experiments show that our PFFN achieves the best performance against all existing lightweight state-of-the-art SR methods with less number of parameters and even performs comparably to computationally expensive networks.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Maisie完成签到,获得积分10
2秒前
小蛇玩发布了新的文献求助10
3秒前
乐观的饭饭完成签到 ,获得积分10
4秒前
4秒前
迷路的含桃完成签到 ,获得积分10
4秒前
幽默的青槐完成签到 ,获得积分10
5秒前
5秒前
tyj完成签到,获得积分10
6秒前
Mmxn发布了新的文献求助10
6秒前
希望天下0贩的0应助苏甜采纳,获得10
6秒前
搞怪绿柳发布了新的文献求助10
6秒前
pluto应助糖果采纳,获得10
7秒前
8秒前
鲤鱼灵阳完成签到,获得积分10
8秒前
Frank应助懒得起名采纳,获得10
8秒前
无花果应助归海亦云采纳,获得10
8秒前
不懂发布了新的文献求助10
9秒前
9秒前
隐形曼青应助小fu采纳,获得10
10秒前
烟花应助SUKAILIMAI采纳,获得10
10秒前
科研通AI5应助Pendragon采纳,获得10
10秒前
小蘑菇应助Jmting采纳,获得10
10秒前
CodeCraft应助小夭采纳,获得10
11秒前
Mmxn完成签到,获得积分10
11秒前
11秒前
在水一方应助jojokin采纳,获得10
13秒前
聪明的鹤发布了新的文献求助10
13秒前
皮皮最可爱完成签到 ,获得积分10
13秒前
睡不醒的喵完成签到,获得积分10
14秒前
14秒前
云岫发布了新的文献求助10
15秒前
迷路的枫完成签到 ,获得积分10
17秒前
17秒前
SH完成签到,获得积分10
17秒前
17秒前
不懂完成签到,获得积分20
18秒前
Jmting完成签到,获得积分10
18秒前
18秒前
三分糖完成签到,获得积分20
19秒前
明亮紫易发布了新的文献求助10
19秒前
高分求助中
Comparative Anatomy of the Vertebrates 9th 3000
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Les Mantodea de Guyane Insecta, Polyneoptera 1000
Structural Load Modelling and Combination for Performance and Safety Evaluation 1000
Conference Record, IAS Annual Meeting 1977 820
England and the Discovery of America, 1481-1620 600
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3571872
求助须知:如何正确求助?哪些是违规求助? 3142287
关于积分的说明 9446687
捐赠科研通 2843683
什么是DOI,文献DOI怎么找? 1562971
邀请新用户注册赠送积分活动 731530
科研通“疑难数据库(出版商)”最低求助积分说明 718557