Supervise-Assisted Self-Supervised Deep-Learning Method for Hyperspectral Image Restoration

高光谱成像 人工智能 计算机科学 深度学习 图像(数学) 模式识别(心理学) 计算机视觉
作者
Miaoyu Li,Ying Fu,Tao Zhang,Guanghui Wen
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:36 (4): 7331-7344 被引量:41
标识
DOI:10.1109/tnnls.2024.3386809
摘要

Hyperspectral image (HSI) restoration is a challenging research area, covering a variety of inverse problems. Previous works have shown the great success of deep learning in HSI restoration. However, facing the problem of distribution gaps between training HSIs and target HSI, those data-driven methods falter in delivering satisfactory outcomes for the target HSIs. In addition, the degradation process of HSIs is usually disturbed by noise, which is not well taken into account in existing restoration methods. The existence of noise further exacerbates the dissimilarities within the data, rendering it challenging to attain desirable results without an appropriate learning approach. To track these issues, in this article, we propose a supervise-assisted self-supervised deep-learning method to restore noisy degraded HSIs. Initially, we facilitate the restoration network to acquire a generalized prior through supervised learning from extensive training datasets. Then, the self-supervised learning stage is employed and utilizes the specific prior of the target HSI. Particularly, to restore clean HSIs during the self-supervised learning stage from noisy degraded HSIs, we introduce a noise-adaptive loss function that leverages inner statistics of noisy degraded HSIs for restoration. The proposed noise-adaptive loss consists of Stein's unbiased risk estimator (SURE) and total variation (TV) regularizer and fine-tunes the network with the presence of noise. We demonstrate through experiments on different HSI tasks, including denoising, compressive sensing, super-resolution, and inpainting, that our method outperforms state-of-the-art methods on benchmarks under quantitative metrics and visual quality. The code is available at https://github.com/ying-fu/SSDL-HSI.
最长约 10秒,即可获得该文献文件

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
桐桐的应助被霸气雯采纳,获得10
1秒前
iwhisper完成签到,获得积分10
1秒前
1秒前
Xx完成签到,获得积分20
2秒前
桐桐的应助被热心宛菡采纳,获得10
2秒前
ki发布了新的文献求助10
2秒前
orixero的应助被停云采纳,获得10
2秒前
kjh完成签到,获得积分10
4秒前
小唐人完成签到,获得积分10
4秒前
5秒前
大卫和小草完成签到,获得积分10
5秒前
丘比特的应助被怪力花生采纳,获得30
5秒前
斯文败类的应助被xuxu采纳,获得50
5秒前
水煮电吹风的应助被Xx采纳,获得10
6秒前
master发布了新的文献求助10
7秒前
小马甲的应助被runrun采纳,获得10
8秒前
研友_LkqbzZ发布了新的文献求助10
8秒前
隋玉发布了新的文献求助10
8秒前
Owen的应助被runrun采纳,获得10
8秒前
SciGPT的应助被runrun采纳,获得10
8秒前
Akim的应助被runrun采纳,获得10
8秒前
FashionBoy的应助被runrun采纳,获得10
8秒前
8秒前
彭于晏的应助被runrun采纳,获得10
8秒前
kk子的应助被runrun采纳,获得10
9秒前
9秒前
小马甲的应助被runrun采纳,获得10
9秒前
Gibson发布了新的文献求助10
9秒前
斯文败类的应助被runrun采纳,获得10
9秒前
汉堡包的应助被runrun采纳,获得10
9秒前
ZZZ完成签到 ,获得积分10
9秒前
十八寒露的应助被LEETHEO采纳,获得10
10秒前
科研通AI6.3的应助被溧谦采纳,获得10
10秒前
许鑫蓁完成签到 ,获得积分10
11秒前
long-zhang完成签到,获得积分10
12秒前
俏皮诺言发布了新的文献求助10
12秒前
tjzbw发布了新的文献求助10
13秒前
烟花的应助被ZBN采纳,获得10
13秒前
sun完成签到,获得积分10
13秒前
xing_xing的应助被qrj采纳,获得20
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183601
求助须知:如何正确求助?哪些是违规求助? 9572875
关于积分的说明 21827816
捐赠科研通 7780716
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558197
邀请新用户注册赠送积分活动 2480485