ITER: Image-to-pixel Representation for Weakly Supervised HSI Classification

像素 人工智能 计算机科学 模式识别(心理学) 高光谱成像 上下文图像分类 特征(语言学) 特征提取 注释 水准点(测量) 计算机视觉 图像(数学) 地理 哲学 语言学 大地测量学
作者
Jiaqi Yang,Bo Du,Di Wang,Liangpei Zhang
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:33: 257-272
标识
DOI:10.1109/tip.2023.3326699
摘要

Recent years have witnessed the superiority of deep learning-based algorithms in the field of HSI classification. However, a prerequisite for the favorable performance of these methods is a large number of refined pixel-level annotations. Due to atmospheric changes, sensor differences, and complex land cover distribution, pixel-level labeling of high-dimensional hyperspectral image (HSI) is extremely difficult, time-consuming, and laborious. To overcome the above hurdle, an Image-To-pixEl Representation (ITER) approach is proposed in this paper. To the best of our knowledge, this is the first time that image-level annotation is introduced to predict pixel-level classification maps for HSI. The proposed model is along the lines of subject modeling to boundary refinement, corresponding to pseudo-label generation and pixel-level prediction. Concretely, in the pseudo-label generation part, the spectral/spatial activation, spectral-spatial alignment loss, and geographic element enhancement are sequentially designed to locate discriminate regions of each category, optimize multi-domain class activation map (CAM) collaborative training, and refine labels, respectively. For the pixel-level prediction portion, a high frequency-aware self-attention in a high-enhanced transformer is put forward to achieve detailed feature representation. With the two-stage pipeline, ITER explores weakly supervised HSI classification with image-level tags, bridging the gap between image-level annotation and dense prediction. Extensive experiments in three benchmark datasets with state-of-the-art (SOTA) works show the performance of the proposed approach.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
2秒前
王紫绯发布了新的文献求助10
6秒前
wyuxilong完成签到,获得积分10
7秒前
mc完成签到,获得积分10
8秒前
9秒前
Orange应助甜蜜的物语采纳,获得10
10秒前
14秒前
14秒前
15秒前
15秒前
berg发布了新的文献求助10
16秒前
壳米应助科研通管家采纳,获得10
18秒前
18秒前
newfat应助科研通管家采纳,获得30
18秒前
18秒前
18秒前
FashionBoy应助科研通管家采纳,获得10
18秒前
Mystic发布了新的文献求助10
18秒前
李爱国应助科研通管家采纳,获得30
18秒前
传奇3应助科研通管家采纳,获得10
18秒前
斯文败类应助科研通管家采纳,获得10
18秒前
Owen应助科研通管家采纳,获得10
18秒前
天天快乐应助科研通管家采纳,获得10
18秒前
Sschi应助科研通管家采纳,获得20
18秒前
18秒前
烟花应助科研通管家采纳,获得10
18秒前
勤劳丹秋发布了新的文献求助10
19秒前
21秒前
22秒前
hs完成签到,获得积分10
25秒前
26秒前
26秒前
李健应助Mystic采纳,获得10
26秒前
orixero应助勤劳丹秋采纳,获得10
27秒前
30秒前
ly发布了新的文献求助10
31秒前
31秒前
健忘熠彤发布了新的文献求助30
32秒前
甜蜜的物语完成签到,获得积分10
32秒前
34秒前
高分求助中
请在求助之前详细阅读求助说明!!!! 20000
Sphäroguß als Werkstoff für Behälter zur Beförderung, Zwischen- und Endlagerung radioaktiver Stoffe - Untersuchung zu alternativen Eignungsnachweisen: Zusammenfassender Abschlußbericht 1500
One Man Talking: Selected Essays of Shao Xunmei, 1929–1939 1000
Yuwu Song, Biographical Dictionary of the People's Republic of China 700
[Lambert-Eaton syndrome without calcium channel autoantibodies] 520
The Three Stars Each: The Astrolabes and Related Texts 500
india-NATO Dialogue: Addressing International Security and Regional Challenges 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 有机化学 工程类 生物化学 纳米技术 物理 内科学 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 电极 光电子学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 2470041
求助须知:如何正确求助?哪些是违规求助? 2137084
关于积分的说明 5445290
捐赠科研通 1861367
什么是DOI,文献DOI怎么找? 925748
版权声明 562721
科研通“疑难数据库(出版商)”最低求助积分说明 495201