Image and Video Processing · arXiv:2611.16802 v1 · submitted 12 Nov 2026 · 83 references
CODE-PIF: Convex/Deep (CODE) Multiview Pseudoinvariant Features for Multitemporal Multispectral Surface Reflectance Imagery
The paper says
“Multitemporal multispectral surface reflectance imagery exhibits radiometric and spectral variability due to atmospheric effects, sensor differences, and actual surface changes, complicating the identification of pseudoinvariant features (PIFs).”
more of the abstract
The SOTA DeepMGCCA captures nonlinear dependencies across acquisition dates, but similarity in its learned feature space does not directly establish consistency in the original reflectance domain. Meanwhile, we believe that the PIFs extracted by DeepMGCCA preserve essential structural characteristics, providing an effective prior to guide subsequent refinement. Therefore, we propose the CODE-PIF architecture, an unsupervised convex/deep (CODE) framework that refines the coarse PIF from DeepMGCCA using convex optimization. Specifically, CODE-PIF uses the data-fitting term to integrate reflectance deviations, correlation-weighted spectral angles, and temporal reference change information to promote radiometric and spectral consistency between predicted PIFs and observed data. Moreover, the regularization term uses a mathematically simple Q-quadratic norm to incorporate information from the coarse PIF estimate into the refined solution. The resulting convex optimization problem is solved using the ADMM optimizer, which decomposes it into simpler subproblems and provides convergence guarantees under standard assumptions. Experiments across four distinct ROIs show improved average radiometric and spectral agreement relative to DeepMGCCA.Averaged across these regions, the RMSE decreases from 0.0192 to 0.0164, PSNR increases from 35.91 to 37.44 dB, and the between-date spectral angle decreases from 3.77 to 2.97 degrees. Although structural similarity and Pearson correlation do not improve in every scene, the results suggest that using observed data helps select PIFs with more consistent reflectance values and spectral shapes across dates.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
CODE-PIF is a clean, incremental refinement of PIF selection for remote sensing. The convex optimization step is well-derived and the experiments are honest, but the circularity in the data-fidelity map is real and unquantified, and the comparison to only one baseline limits the strength of the claims. This line is wrong
the referee pass did not run
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 83 references say.
What would settle it
Re-run the CODE-PIF pipeline on the same four ROIs but with one spectral band (e.g., SWIR-2) excluded from the data-fidelity map construction (Eq. 3–6) and used only as a hold-out for evaluation. If the RMSE and SAM_h improvements on the held-out band are comparable to those reported in Table 3, the circularity concern is mitigated. If improvements vanish or reverse on the held-out band, the reported gains are partly an artifact of fitting the evaluation criterion.
from the skeptic's reading
How the review went
3 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic agrees
- Editor wrote the verdict above
Not run on this paper: the referee, the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
Hi,
You asked about arXiv:2611.16802. Here's my read.
What's new: The paper takes a standard deep PIF method (DeepMGCCA, from the same group) and adds a convex refinement step that re-ranks candidate pixels using a data-fidelity map built from spectral angles and temporal-reference deviations. The ADMM derivation is clean, the Q-quadratic regularizer is simple, and the whole thing is unsupervised. That's a legitimate incremental contribution.
What it does well: The experiments are honest. They use four diverse ROIs, keep the selection fraction fixed, and report multiple metrics. The scatterplots are informative and the authors openly discuss where their method hurts Pearson correlation (Taipei, Tainan) while improving RMSE and spectral angle. The limitation section (3.5) is unusually candid—they acknowledge that the data-fidelity map can be unreliable under widespread change, that the results don't independently establish physical invariance, and that independent temporal verification is needed. That's good practice.
Where the soft spots are: The main one is the circularity in the data-fidelity map (Eq. 6). The map is computed from the same reflectance observations that are later used to evaluate RMSE, PSNR, and SAM_h. The stress-test note is right to flag this. The paper acknowledges the risk but never quantifies it. A held-out band or an independent date pair would have been straightforward and would have made the claim of 'state-of-the-art performance' much stronger. Without that, the reported gains (RMSE -0.003, PSNR +1.5 dB) could partly reflect overfitting to the evaluation metrics.
Second, the comparison is only against DeepMGCCA. That's the natural baseline, but the paper claims 'state-of-the-art' without comparing to, say, IR-MAD or a simple spectral-angle threshold. The authors cite those methods but don't benchmark them. That weakens the novelty claim.
Third, the hyperparameters (lambda, c, tau, K, M, w1-w4) are set without sensitivity analysis. The paper would be stronger with a brief ablation or a robustness check.
Who this is for: Remote sensing practitioners who do relative radiometric normalization and want a drop-in refinement for an existing deep PIF pipeline. The method is easy to implement and the code appears to be available.
Recommendation: This paper deserves peer review. It's a solid incremental method with honest reporting. The circularity concern is real but not fatal—it's a common issue in unsupervised PIF selection. A reviewer should ask for a sensitivity analysis and ideally a held-out validation, but the core idea is sound. I'd accept a review invitation.
Best,
[Your name]
The strongest objection
The central claim is that CODE-PIF improves radiometric and spectral agreement relative to DeepMGCCA. The data-fidelity map (Eq. 6) is constructed from the observed reflectance data itself—specifically, from spectral angles and temporal-reference deviations computed on the same multitemporal images that are later used to evaluate RMSE, PSNR, and SAM_h. This creates a circular dependency: the refinement selects pixels that minimize the very discrepancies that the evaluation metrics measure. The paper acknowledges this risk (Section 3.5: 'the reflectance-derived change scores... may also become unreliable under widespread surface change'), but does not quantify how much of the reported improvement is attributable to this circularity rather than to genuine selection of physically invariant pixels. The concern is load-bearing because if the improvement is largely an artifact of optimizing on the evaluation data, then the claim of 'state-of-the-art performance' (Section 4) is overstated. The paper's own limitation statement (Section 3.5) that the results 'do not independently establish the physical invariance of every selected pixel' underscores this gap. A concrete test would be to evaluate CODE-PIF on an independent set of dates or using a held-out spectral band not used in constructing the fidelity map.
The reader's weakest_assumption identifies that the data-fidelity map 'is computed from the observed reflectance data itself, without independent validation that the chosen spectral angle and temporal reference formulation correctly identify truly invariant pixels.' This is precisely the circularity concern I have articulated. The reader's verdict is CONDITIONAL, and my analysis supports that same verdict: the paper's central claim is plausible but not yet fully secured because the circularity is acknowledged but unquantified. I do not recommend a change to REJECT because the paper provides clear derivations, reasonable experiments, and explicit limitations; the concern is real but addressable with a straightforward hold-out test. I agree with the reader's assessment that additional baselines and sensitivity analysis would strengthen the paper, but the most load-bearing single concern is the circularity between the data-fidelity map and the evaluation metrics. The concrete test I propose (hold-out band evaluation) directly addresses this concern without requiring new data or re-proving published results.
Pith's reading of the paper (a machine's summary, not the authors')
When comparing satellite images taken on different dates, scientists need to identify pixels that have not changed (pseudoinvariant features, or PIFs) to calibrate the images. A recent deep learning method called DeepMGCCA finds candidate PIFs by learning a shared representation across dates, but similarity in that learned space does not guarantee that the actual reflectance values match. CODE-PIF takes the initial PIFs from DeepMGCCA and refines them using a convex optimization that directly compares reflectance values and spectral angles across dates. The optimization uses a data-fitting term that penalizes pixels with large spectral differences and a regularization term that keeps the solution close to the deep learning prior. The resulting continuous scores are then thresholded to select the final PIFs. Experiments on four regions (Turkey, Taipei, Tainan, Saudi Arabia) show that CODE-PIF reduces the average root-mean-square error from 0.0192 to 0.0164 and the between-date spectral angle from 3.77 to 2.97 degrees, while increasing PSNR from 35.91 to 37.44 dB. However, structural similarity and Pearson correlation do not improve in every scene, and the method inherits limitations from both the deep learning prior and the hand-crafted data-fidelity map.
Core claim. CODE-PIF achieves state-of-the-art performance in pseudoinvariant feature selection for multitemporal multispectral surface reflectance imagery, as evidenced by improved average radiometric and spectral agreement across four geographically distinct regions: RMSE decreases from 0.0192 to 0.0164, PSNR increases from 35.91 to 37.44 dB, and between-date spectral angle decreases from 3.77 to 2.97 degrees (Section 3.4, Table 3).
The premise it rests on. The data-fidelity map (Eq. 6) constructed from correlation-weighted spectral angles and temporal-reference deviations reliably indicates pixel invariance across dates. This map is computed from the observed reflectance data itself, without independent validation that the chosen spectral angle and temporal reference formulation correctly identify truly invariant pixels. The paper acknowledges that this map may become unreliable under widespread surface change, persistent contamination, or substantial registration errors (Section 3.5).
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Multitemporal multispectral surface reflectance imagery exhibits radiometric and spectral variability due to atmospheric effects, sensor differences, and actual surface changes, complicating the identification of pseudoinvariant features (PIFs). The SOTA DeepMGCCA captures nonlinear dependencies across acquisition dates, but similarity in its learned feature space does not directly establish consistency in the original reflectance domain. Meanwhile, we believe that the PIFs extracted by DeepMGCCA preserve essential structural characteristics, providing an effective prior to guide subsequent refinement. Therefore, we propose the CODE-PIF architecture, an unsupervised convex/deep (CODE) framework that refines the coarse PIF from DeepMGCCA using convex optimization. Specifically, CODE-PIF uses the data-fitting term to integrate reflectance deviations, correlation-weighted spectral angles, and temporal reference change information to promote radiometric and spectral consistency between predicted PIFs and observed data. Moreover, the regularization term uses a mathematically simple Q-quadratic norm to incorporate information from the coarse PIF estimate into the refined solution. The resulting convex optimization problem is solved using the ADMM optimizer, which decomposes it into simpler subproblems and provides convergence guarantees under standard assumptions. Experiments across four distinct ROIs show improved average radiometric and spectral agreement relative to DeepMGCCA.Averaged across these regions, the RMSE decreases from 0.0192 to 0.0164, PSNR increases from 35.91 to 37.44 dB, and the between-date spectral angle decreases from 3.77 to 2.97 degrees. Although structural similarity and Pearson correlation do not improve in every scene, the results suggest that using observed data helps select PIFs with more consistent reflectance values and spectral shapes across dates.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 0.79
“Although structural similarity and Pearson correlation do not improve in every scene, the results suggest that using observed data helps select PIFs with more consistent reflectance values and spectral shapes across dates.”
How the main claim is stated: hedged possibility 1.00
What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.92 · human participants 0.02 · controlled comparison 0.88 · randomized assignment 0.01 · states quantitative result 0.99 · compares with prior results 0.98 · mentions code or data availability 0.02
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Multitemporal multispectral surface reflectance imagery exhibits radiometric and spectral variability due to atmospheric effects, sensor differences, and actual surface changes, complicating the identification of pseudoinvariant features (PIFs). | background 1.00 | 0.06 | 0.02 | asserted 1.00 |
| The SOTA DeepMGCCA captures nonlinear dependencies across acquisition dates, but similarity in its learned feature space does not directly establish consistency in the original reflectance domain. | gap 0.67 | 0.08 | 0.04 | asserted 1.00 |
| Meanwhile, we believe that the PIFs extracted by DeepMGCCA preserve essential structural characteristics, providing an effective prior to guide subsequent refinement. | interpretation 0.42 | 0.18 | 0.06 | speculative 0.61 |
| Therefore, we propose the CODE-PIF architecture, an unsupervised convex/deep (CODE) framework that refines the coarse PIF from DeepMGCCA using convex optimization. | contribution 0.98 | 0.84 | 0.13 | asserted 1.00 |
| Specifically, CODE-PIF uses the data-fitting term to integrate reflectance deviations, correlation-weighted spectral angles, and temporal reference change information to promote radiometric and spectral consistency between predicted PIFs and observed data. | method 1.00 | 0.82 | 0.05 | asserted 1.00 |
| Moreover, the regularization term uses a mathematically simple Q-quadratic norm to incorporate information from the coarse PIF estimate into the refined solution. | method 1.00 | 0.83 | 0.03 | asserted 1.00 |
| The resulting convex optimization problem is solved using the ADMM optimizer, which decomposes it into simpler subproblems and provides convergence guarantees under standard assumptions. | method 1.00 | 0.69 | 0.03 | asserted 0.99 |
| Experiments across four distinct ROIs show improved average radiometric and spectral agreement relative to DeepMGCCA.Averaged across these regions, the RMSE decreases from 0.0192 to 0.0164, PSNR increases from 35.91 to 37.44 dB, and the between-date spectral angle decreases from 3.77 to 2.97 degrees. | result 1.00 | 0.96 | 0.43 | asserted 1.00 |
| Although structural similarity and Pearson correlation do not improve in every scene, the results suggest that using observed data helps select PIFs with more consistent reflectance values and spectral shapes across dates. | interpretation 0.93 | 0.95 | 0.53 | hedged possibility 1.00 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.83
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 7,307 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (6)
Figures are the authors', reproduced from the paper.
References (83)
- [1] Yuan, Ding and Elvidge, Christopher D. , journal =. 1996 , volume =. doi:10.1016/0924-2716(96)00018-4 , priority = on Pithdoi:10.1016/0924-2716(96)00018-4
- [2] Lin, Chia-Hsiang and Liu, Yangrui and Chi, Chong-Yung and Hsu, Chih-Chung and Ren, Hsuan and Quek, Tony Q. S. , journal=. Hyperspectral Tensor Completion Using Low-Rank Modeling and Convex Functional Analysis , year= on Pith
- [3] Lin, Chia-Hsiang and Young, Si-Sheng , journal=. Hyper. Apr. 2025 , publisher= on Pith
- [4] Lin, Chia-Hsiang and Young, Si-Sheng , journal=. Underdetermined Blind Source Separation via Weighted Simplex Shrinkage Regularization and Quantum Deep Image Prior , year= on Pith
- [5] Rahman, M.M. and Hay, G.J. and Couloigner, I. and Hemachandran, B. and Bailin, J. , journal =. 2015 , volume =. doi:10.1016/j.isprsjprs.2015.05.002 , priority = on Pithdoi:10.1016/j.isprsjprs.2015.05.002
- [6] Guindon, B. , title =. ISPRS J. Photogramm. Remote Sens. , year =. doi:10.1016/s0924-2716(97)00016-6 , priority = on Pithdoi:10.1016/s0924-2716(97)00016-6
- [7] Lin, Chao-Hung and Lin, Bo-Yi and Lee, Kuan-Yi and Chen, Yi-Chen , journal =. 2015 , volume =. doi:10.1016/j.isprsjprs.2015.05.003 , priority = on Pithdoi:10.1016/j.isprsjprs.2015.05.003
- [8] Syariz, Muhammad Aldila and Lin, Bo-Yi and Denaro, Lino Garda and Jaelani, Lalu Muhamad and Van Nguyen, Manh and Lin, Chao-Hung , journal =. 2019 , volume =. doi:10.1016/j.isprsjprs.2018.11.007 , priority = on Pithdoi:10.1016/j.isprsjprs.2018.11.007
- [9] Clark, Barnaby and Suomalainen, Juha and Pellikka, Petri , title =. ISPRS J. Photogramm. Remote Sens. , year =. doi:10.1016/j.isprsjprs.2011.02.003 , priority = on Pithdoi:10.1016/j.isprsjprs.2011.02.003
- [10] Lin, Chia-Hsiang and Hsu, Chih-Chung and Young, Si-Sheng and Hsieh, Cheng-Ying and Tai, Shen-Chieh , journal=. Mar. 2024 , volume= on Pith
- [11] Mei, Alessandro and Bassani, Cristiana and Fontinovo, Giuliano and Salvatori, Rosamaria and Allegrini, Alessia , title =. ISPRS J. Photogramm. Remote Sens. , year =. doi:10.1016/j.isprsjprs.2016.01.016 , priority = on Pithdoi:10.1016/j.isprsjprs.2016.01.016
- [12] Lin, Chia-Hsiang and Huang, Shih-Hsiu and Lin, Ting-Hsuan and Wu, Pin-Chieh , journal=. Metasurface-empowered snapshot hyperspectral imaging with convex/deep. Nov. 2023 , publisher= on Pith
- [13] Xu, Qing and Hou, Zhengyang and Tokola, Timo , title =. ISPRS J. Photogramm. Remote Sens. , year =. doi:10.1016/j.isprsjprs.2011.12.008 , priority = on Pithdoi:10.1016/j.isprsjprs.2011.12.008
- [14] Eivazi, Anna and Kolesnikov, Alexander and Junttila, Virpi and Kauranne, Tuomo , title =. ISPRS J. Photogramm. Remote Sens. , year =. doi:10.1016/j.isprsjprs.2015.03.007 , priority = on Pithdoi:10.1016/j.isprsjprs.2015.03.007
- [15] Volpi, Michele and Camps-Valls, Gustau and Tuia, Devis , journal =. 2015 , volume =. doi:10.1016/j.isprsjprs.2015.02.005 , priority = on Pithdoi:10.1016/j.isprsjprs.2015.02.005
- [16] Yu, Lei and Zhang, Yongjun and Sun, Mingwei and Zhou, Xiuguang and Liu, Chi , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [17] Lin, Dekun and Shen, Huanfeng and Li, Xinghua and Zeng, Chao and Jiang, Tao and Ma, Yongming and Xu, Mingjie , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [18] Boyd, Stephen and Parikh, Neal and Chu, Eric and Peleato, Borja and Eckstein, Jonathan , journal =. 2011 , volume = on Pith
- [19] Morton J Canty and Allan A Nielsen and Michael Schmidt , keywords =. Automatic radiometric normalization of multitemporal satellite imagery , journal =. 2004 , issn =. doi:https://doi.org/10.1016/j.rse.2003.10.024 , url = on Pithdoi:10.1016/j.rse.2003.10.024
- [20] Morton J. Canty and Allan A. Nielsen , keywords =. Automatic radiometric normalization of multitemporal satellite imagery with the iteratively re-weighted MAD transformation , journal =. 2008 , issn =. doi:https://doi.org/10.1016/j.rse.2007.07.013 , url = on Pithdoi:10.1016/j.rse.2007.07.013
show 63 more
- [21] Xu, Jianjian and Liu, Tongfei and Lei, Tao and Chen, Hongruixuan and Yokoya, Naoto and Lv, Zhiyong and Gong, Maoguo , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [22] Fang, Bo and Chen, Gang and Kou, Rong and Paoletti, Mercedes E. and Haut, Juan M. and Plaza, Antonio , journal =. 2023 , volume = on Pith
- [23] Zheng, Zhi and Wan, Yi and Zhang, Yongjun and Xiang, Sizhe and Peng, Daifeng and Zhang, Bin , journal =. 2021 , volume = on Pith
- [24] Lin, Chia-Hsiang and Lin, Yen-Cheng and Tang, Po-Wei , journal=. 2021 , publisher= on Pith
- [25] Lin, Tzu-Hsuan and Lin, Chia-Hsiang , journal=. Hyperspectral Change Detection Using Semi-Supervised Graph Neural Network and Convex Deep Learning , year= on Pith
- [26] Lin, Chia-Hsiang and Bioucas-Dias, Jos. An explicit and scene-adapted definition of convex self-similarity prior with application to unsupervised. IEEE Trans. Geosci. Remote Sens. , volume=. Dec. 2019 , publisher= on Pith
- [27] An algorithm for total variation minimization and applications , author=. Journal of Mathematical Imaging and Vision , volume=. Jan. 2004 , publisher= on Pith
- [28] Lin, Chia-Hsiang and Chu, Man-Chun and Tang, Po-Wei , journal=. 2023 , volume= on Pith
- [29] Chi, Chong-Yung and Li, Wei-Chiang and Lin, Chia-Hsiang , publisher =. 2017 , doi = on Pith
- [30] Li, Zhiwei and Shen, Huanfeng and Weng, Qihao and Zhang, Yuzhuo and Dou, Peng and Zhang, Liangpei , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [31] Zhai, Han and Zhang, Hongyan and Zhang, Liangpei and Li, Pingxiang , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [32] Zhang, Chenxiao and Yue, Peng and Tapete, Deodato and Jiang, Liangcun and Shangguan, Boyi and Huang, Li and Liu, Guangchao , journal =. 2020 , volume = on Pith
- [33] Zhang, Erlei and Li, Xinyu and Zong, He and Gao, Yuan and Ren, Jinchang , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [34] Zhang, Puzhao and Gong, Maoguo and Su, Linzhi and Liu, Jia and Li, Zhizhou , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [35] Zheng, Zhuo and Zhong, Yanfei and Zhao, Ji and Ma, Ailong and Zhang, Liangpei , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [36] Denaro, Lino Garda and Lin, Bo-Yi and Syariz, Muhammad Aldila and Jaelani, Lalu Muhamad and Lin, Chao-Hung , title =. Journal of Applied Remote Sensing , volume =. 2018 , month =. doi:10.1117/1.JRS.12.045002 , url = on Pithdoi:10.1117/1.jrs.12.045002
- [37] Denaro, Lino Garda and Lin, Chao-Hung , journal=. Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Imagery , year= on Pith
- [38] HYBRID CANONICAL CORRELATION ANALYSIS AND REGRESSION FOR RADIOMETRIC NORMALIZATION OF CROSS-SENSOR SATELLITE IMAGES , author =. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences , year = on Pith
- [39] Denaro, Lino Garda and Lin, Chao-Hung , booktitle=. 2019 , volume= on Pith
- [40] Denaro, Lino Garda and Syariz, Muhammad Aldila and Nabilah, Salwa and Heriza, Dewinta and Lin, Chao-Hung , journal =. 2019 , volume = on Pith
- [41] Chen, Pan and Zhang, Bing and Hong, Danfeng and Chen, Zhengchao and Yang, Xuan and Li, Baipeng , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [42] Chen, Hongruixuan and Yokoya, Naoto and Chini, Marco , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [43] Li, Li and Xia, Menghan and Liu, Chi and Li, Liang and Wang, Hanyun and Yao, Jian , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [44] Sun, Yuli and Lei, Lin and Tan, Xiang and Guan, Dongdong and Wu, Junzheng and Kuang, Gangyao , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [45] Xie, Renping and Xia, Menghan and Yao, Jian and Li, Li , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [46] Radiometric rectification: Toward a common radiometric response among multidate, multisensor images , journal =. 1991 , issn =. doi:https://doi.org/10.1016/0034-4257(91)90062-B , url = on Pithdoi:10.1016/0034-4257(91)90062-b
- [47] Cheng, Hongquan and Wu, Huayi and Zheng, Jie and Qi, Kunlun and Liu, Wenxuan , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [48] Relations among m Sets of Measures , volume=. Psychometrika , author=. 1961 , pages=. doi:10.1007/BF02289710 , number= on Pithdoi:10.1007/bf02289710
- [49] Hussain, Masroor and Chen, Dongmei and Cheng, Angela and Wei, Hui and Stanley, David , journal =. 2013 , volume = on Pith
- [50] Lin, Chia-Hsiang and Hsu, Shih-Min and Liang, Ching-Yun and Chanussot, Jocelyn and Chen, Jhih-Yan , journal=. Hyperspectral Calibration Detection: A Novel Concept for Change Detection With Unsupervised Incremental Safe Pseudo-Labeling Implementation , year= on Pith
- [51] Lin, Chia-Hsiang and Chen, You-Yao , journal=. 2023 , publisher= on Pith
- [52] Chen, Hongruixuan and Song, Jian and Wu, Chen and Du, Bo and Yokoya, Naoto , journal =. 2023 , volume = on Pith
- [53] Lin, Chia-Hsiang and Lin, Jhao-Ting and Chiu, Po-Ying and Chen, Shih-Ping and Lin, Charles CH , journal=. Quantum-Driven Multihead Inland Waterbody Detection With Transformer-Encoded. 2025 , publisher= on Pith
- [54] Trevisiol, F. and Mandanici, E. and Pagliarani, A. and Bitelli, G. , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [55] Zhan, Tao and Gong, Maoguo and Liu, Jia and Zhang, Puzhao , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [56] Yan, Lin and Roy, David P. and Huang, Haiyan , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [57] Ma, Lei and Liu, Yu and Zhang, Xueliang and Ye, Yuanxin and Yin, Gaofei and Johnson, Brian Alan , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [58] Razzak, Muhammed T. and Mateo-Garc. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [59] Multivariate Alteration Detection. Remote Sensing of Environment , volume =. 1998 , issn =. doi:https://doi.org/10.1016/S0034-4257(97)00162-4 , url = on Pithdoi:10.1016/s0034-4257(97)00162-4
- [60] Tuia, Devis and Marcos, Diego and Camps-Valls, Gustau , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [61] Miao, Jianhao and Li, Shuang and Bai, Xuechen and Gan, Wenxia and Wu, Jianwei and Li, Xinghua , journal =. 2025 , volume = on Pith
- [62] Zhang, Lin and Hu, Xiangyun and Zhang, Mi and Shu, Zhen and Zhou, Hao , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [63] Li, Yinxuan and Yin, Hongche and Yao, Jian and Wang, Hanyun and Li, Li , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [64] Zhao, Chenyang and Goshtasby, A. Ardeshir , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [65] John R. Schott and Carl Salvaggio and William J. Volchok , abstract =. Radiometric scene normalization using pseudoinvariant features , journal =. 1988 , issn =. doi:https://doi.org/10.1016/0034-4257(88)90116-2 , url = on Pithdoi:10.1016/0034-4257(88)90116-2
- [66] Sun, Yuli and Lei, Lin and Li, Zhang and Kuang, Gangyao , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [67] Du, Peijun and Wang, Xin and Chen, Dongmei and Liu, Sicong and Lin, Cong and Meng, Yaping , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [68] Tu, Lilin and Huang, Xin and Li, Jiayi and Yang, Jie and Gong, Jianya , journal =. 2024 , volume = on Pith
- [69] Obata, Kenta and Yoshioka, Hiroki , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [70] Gan, Wenxia and Feng, Yu and Miao, Jianhao and Li, Xinghua and Shen, Huanfeng , title =. ISPRS J. Photogramm. Remote Sens. , year = on Pith
- [71] Benton, Adrian and Khayrallah, Huda and Gujral, Biman and Reisinger, Dee Ann and Zhang, Sheng and Arora, Raman. Deep Generalized Canonical Correlation Analysis. Proc. Workshop on Representation Learning for NLP. 2019. doi:10.18653/v1/W19-4301 on Pithdoi:10.18653/v1/w19-4301
- [72] Denaro, Lino Garda and Lin, Chao-Hung , journal=. Constrained Harmonization of Optical Satellite Imagery for Surface Reflectance Bias Removal , year= on Pith
- [73] Du, Yong and Teillet, Philippe M. and Cihlar, Josef , title =. Remote Sensing of Environment , year = on Pith
- [74] Denaro, Lino Garda and Lin, Chia-Hsiang , title =. 2026 , month =. 2610.21183 , archivePrefix = on PithPith's reviewarXiv
- [75] Lin, Bo-Yi and Wang, Zhi-Jia and Syariz, Muhammad Aldila and Denaro, Lino Garda and Lin, Chao-Hung , journal=. Pseudoinvariant Feature Selection Using Multitemporal MAD for Optical Satellite Images , year= on Pith
- [76] Deep Canonical Correlation Analysis , author =. Proc. International Conference on Machine Learning , pages =. 2013 , editor = on Pith
- [77] On Deep Multi-View Representation Learning , author =. Proc. International Conference on Machine Learning , pages =. 2015 , editor = on Pith
- [78] Sambandham, Venkatesh Thirugnana and Kirchheim, Konstantin and Ortmeier, Frank and Mukhopadhaya, Sayan , journal =. 2024 , volume = on Pith
- [79] Tang, Po-Wei and Lin, Chia-Hsiang and Huang, Jian-Kai and Huete, Alfredo R , journal=. A quantum-empowered. 2025 , publisher= on Pith
- [80] Lin, Chia-Hsiang and Hsieh, Cheng-Ying and Lin, Jhao-Ting , title =. IEEE Trans. Geosci. Remote Sens. , year = on Pith
- [81] Lin, Chia-Hsiang and Chen, Jui-Ting and Leng, Zi-Chao and Lin, Jhao-Ting , title =. 2025 , eprint = on Pith
- [82] Lin, Chia-Hsiang and Liu, Wei-Chih and Chiu, Yu-En and Lin, Jhao-Ting , title =. IEEE Trans. Geosci. Remote Sens. , year = on Pith
- [83] Lin, Chia-Hsiang and Huang, Jian-Kai and Young, Si-Sheng and Zheng, Wei-Cheng , title =. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. , year = on Pith
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment