14.3 Robust Techniques, Robust Classification

Chapter Contents (Back)
Robust Technique. Robust techniques are characterized by the number of errors tolerated. A level of 0% means that single errors in the input data cause errors in the output. 50% would correspond to least median of squares -- half of the data may be bad.
See also Noisy Labels for Learning.
See also Outlier Detection and Analysis, Robust Analysis, Out of Distribution.

Huber, P.J.,
Robust Statistics,
John Wiley&Sons, New York, 1981. The place to start to know what it all means. BibRef 8100

Besl, P.J., Birch, J.B., Watson, L.T.,
Robust Window Operators,
MVA(2), 1989, pp. 179-191. BibRef 8900
Earlier: ICCV88(591-600).
IEEE DOI BibRef

Gupta, L.[Lalit], Sayeh, M.R.[Mohammad R.], Tammana, R.[Ravi],
A Neural Network Approach to Robust Shape Classification,
PR(23), No. 6, 1990, pp. 563-568.
Elsevier DOI 3 layer net. BibRef 9000

Gutfinger, D., Sklansky, J.,
Robust classifiers by mixed adaptation,
PAMI(13), No. 6, June 1991, pp. 552-567.
IEEE DOI BibRef 9106

Zhuang, X., Wang, T., and Zhang, P.,
A Highly Robust Estimator through Partially Likelihood Function Modeling and Its Application in Computer Vision,
PAMI(14), No. 1, January 1992, pp. 19-35.
IEEE DOI BibRef 9201

Zhuang, X., and Zhang, P.,
A Highly Robust Estimator for Computer Vision,
ICPR90(I: 545-550).
IEEE DOI BibRef 9000

Hampshire, II, J.B., and Waibel, A.,
The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multisource Pattern Recognition,
PAMI(14), No. 7, July 1992, pp. 751-769.
IEEE DOI BibRef 9207

Meer, P.[Peter], Mintz, D.[Doron], Kim, D.Y.[Dong Yoon], Rosenfeld, A.[Azriel],
Robust Regression Methods for Computer Vision: A Review,
IJCV(6), No. 1, April 1991, pp. 59-70.
Springer DOI BibRef 9104

Mintz, D., Meer, P., and Rosenfeld, A.,
Consensus by Decomposition: A Paradigm for Fast High Breakdown Point Robust Estimation,
DARPA92(345-362). More on the topic. BibRef 9200

Meer, P.[Peter],
Robust High Breakdown Estimation and Consensus,
AMV Strategies921992, pp. 23-33. See
See also Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. BibRef 9200

Meer, P., Mintz, D., and Rosenfeld, A.,
Analysis of the Least median of Squares Estimator for Computer Vision Applications,
CVPR92(621-623).
IEEE DOI BibRef 9200
Earlier:
Least Median of Squares Based Robust Analysis of Image Structure,
DARPA90(231-254). Least Median. They also have papers in the Robust Vision Workshop on similar topics.
See also Robust Consensus Based Edge-Detection. BibRef

Meer, P., Mintz, D., and Rosenfeld, A.,
Robust Recovery of Precursive Polynomial Image Structure,
Robust90(xx). BibRef 9000

Kim, D.Y., Kim, J.J., Meer, P., Mintz, D., Rosenfeld, A.,
Robust Computer Vision: A Least Median of Squares Based Approach,
DARPA89(1117-1134). BibRef 8900

Mintz, D., Meer, P., and Rosenfeld, A.,
A Fast, High Breakdown Point Robust Estimator for Computer Vision Applications,
DARPA90(255-257). BibRef 9000

Mintz, D.,
Robustness by Consensus,
UMD-CAR-TR-576. 1991. BibRef 9100

Olson, C.F.[Clark F.],
An Approximation Algorithm for Least Median of Squares Regression,
IPL(63), No. 5, September 1997, 237-241.
Elsevier DOI BibRef 9709

Li, S.Z.,
Discontinuous MRF Prior and Robust Statistics: A Comparative-Study,
IVC(13), No. 3, April 1995, pp. 227-233.
Elsevier DOI BibRef 9504

Mount, D.M., Netanyahu, N.S.,
Computationally Efficient Algorithms for High-Dimensional Robust Estimators,
GMIP(56), No. 4, July 1994, pp. 289-303. BibRef 9407

Ney, H.[Hermann], Essen, U.[Ute], Kneser, R.[Reinhard],
On the Estimation of 'Small' Probabilities by Leaving-One-Out,
PAMI(17), No. 12, December 1995, pp. 1202-1212.
IEEE DOI Training samples are less than the number of possible classes. BibRef 9512

Brunelli, R., Messelodi, S.,
Robust Estimation Of Correlation With Applications To Computer Vision,
PR(28), No. 6, June 1995, pp. 833-841.
Elsevier DOI BibRef 9506

Zhou, P., Pycock, D.,
Robust Statistical-Models for Cell Image Interpretation,
IVC(15), No. 4, April 1997, pp. 307-316.
Elsevier DOI 9706
BibRef
Earlier:
Robust Statistical Model-Based Cell Image Interpretation,
BMVC95(xx-yy).
PDF File. 9509
BibRef
And:
Robust Model-Based Boundary Cue Generation for Cell Image Interpretation,
BMVC95(xx-yy).
PDF File. 9509
BibRef

Bosdogianni, P., Petrou, M., Kittler, J.V.,
Mixture-Models with Higher-Order Moments,
GeoRS(35), No. 2, March 1997, pp. 341-353.
IEEE Top Reference. 9704
BibRef

Bosdogianni, P., Petrou, M., Kittler, J.V.,
Mixed Pixel Classification with Robust Statistics,
GeoRS(35), No. 3, May 1997, pp. 551-559.
IEEE Top Reference. 9706
BibRef
Earlier:
Mixed Pixel Classification in Remote Sensing,
SPIE(2315), Image and Signal Processing for Remote Sensing, Rome, September 1994, pp. 494-505. BibRef

Bosdogianni, P., Kalviainen, H., Petrou, M., Kittler, J.V.,
Robust Unmixing of Large Sets of Mixed Pixels,
PRL(18), No. 5, May 1997, pp. 415-424. 9708
BibRef

Bosdogianni, P., Petrou, M., Kittler, J.V.,
Classification of Sets of Mixed Pixels with the Hypothesis-Testing Hough Transform,
VISP(145), No. 1, February 1998, pp. 57-64. 9804

See also Hough Transform Algorithm with a 2D Hypothesis-Testing Kernel, A. BibRef

Kalviainen, H., Bosdogianni, P., Petrou, M., Kittler, J.V.,
Mixed Pixel Classification with the Randomized Hough Transform,
ICPR96(II: 576-580).
IEEE DOI 9608
(Univ. of Surrey, UK) BibRef

Lang, G.K., Seitz, P.,
Robust Classification of Arbitrary Object Classes Based on Hierarchical Spatial Feature-Matching,
MVA(10), No. 3, 1997, pp. 123-135.
Springer DOI 9709
BibRef

Kundur, D., Hatzinakos, D., and Leung, H.,
Robust Classification of Blurred Imagery,
IP(9), No. 2, February 2000, pp. 243-255.
IEEE DOI 0003
BibRef
Earlier:
A Novel Approach to Robust Blind Classification of Remote Sensing Imagery,
ICIP97(III: 130-133).
IEEE DOI BibRef

Meer, P.[Peter], Stewart, C.V.[Charles V.], Tyler, D.E.[David E.],
Robust Computer Vision: An Interdisciplinary Challenge,
CVIU(78), No. 1, April 2000, pp. 1-7.
DOI Link
HTML Version. Robust Techniques. Special Issue introduction. 0004
BibRef

Meer, P.[Peter],
From a robust hierarchy to a hierarchy of robustness,
FIU01(323-347).
HTML Version. BibRef 0100

Kim, M.H.[Mun-Hwa], Jang, D.S.[Dong-Sik], Yang, Y.K.[Young-Kyu],
A robust-invariant pattern recognition model using Fuzzy ART,
PR(34), No. 8, August 2001, pp. 1685-1696.
Elsevier DOI 0105
BibRef

Shoham, S.[Shy],
Robust clustering by deterministic agglomeration EM of mixtures of multivariate t-distributions,
PR(35), No. 5, May 2002, pp. 1127-1142.
Elsevier DOI 0202
BibRef

Li, Y.H.[Yu-Hua], Pont, M.J.[Michael J.], Jones, N.B.[N. Barrie],
Improving the performance of radial basis function classifiers in condition monitoring and fault diagnosis applications where 'unknown' faults may occur,
PRL(23), No. 5, March 2002, pp. 569-577.
Elsevier DOI 0202
BibRef

Wang, Z.D.[Zi-Dong], Liu, X.H.[Xiao-Hui],
Robust stability of two-dimensional uncertain discrete systems,
SPLetters(10), No. 5, May 2003, pp. 133-136.
IEEE Top Reference. 0304
BibRef
And: Corrections: SPLetters(10), No. 8, August 2003, pp. 250-250.
IEEE Abstract. 0308
BibRef

Sebe, N.[Nicu], Lew, M.S.[Michael S.],
Robust Computer Vision Theory and Applications,
KluwerApril 2003. ISBN 1-4020-1293-4.
WWW Link. BibRef 0304

Ouyang, S., Ching, P.C., Lee, T.,
Robust adaptive quasi-Newton algorithms for eigensubspace estimation,
VISP(150), No. 4, October 2003, pp. 321-330.
IEEE Abstract. 0401
BibRef

Li, Y.M.[Yong-Min],
On incremental and robust subspace learning,
PR(37), No. 7, July 2004, pp. 1509-1518.
Elsevier DOI 0405
BibRef

Meer, P.[Peter],
Robust Techniques for Computer Vision,
ETCV04(Chapter 4). BibRef 0400

Ma, J.H.[Jiang-Hong], Leung, Y.[Yee], Luo, J.C.[Jian-Cheng],
A highly robust estimator for regression models,
PRL(27), No. 1, 1 January 2006, pp. 29-36.
Elsevier DOI 0512
BibRef

Fidler, S.[Sanja], Skocaj, D.[Danijel], Leonardis, A.[Aleš],
Combining Reconstructive and Discriminative Subspace Methods for Robust Classification and Regression by Subsampling,
PAMI(28), No. 3, March 2006, pp. 337-350.
IEEE DOI 0602
PCA can help in reconstructing missing data. LDA for classification. BibRef

Skocaj, D.[Danijel], Leonardis, A.[Aleš], Bischof, H.[Horst],
Weighted and robust learning of subspace representations,
PR(40), No. 5, May 2007, pp. 1556-1569.
Elsevier DOI 0702
BibRef
Earlier: A1, A2, Only:
Weighted and robust incremental method for subspace learning,
ICCV03(1494-1501).
IEEE DOI 0311
Appearance-based modeling; Robust learning; Principal component analysis; Weighted PCA; Missing pixels; Robust PCA BibRef

Skocaj, D.[Danijel], Leonardis, A.[Ales],
Incremental and robust learning of subspace representations,
IVC(26), No. 1, 1 January 2008, pp. 27-38.
Elsevier DOI 0711
Subspace learning; Incremental learning; Robust learning BibRef

Skocaj, D.[Danijel], Leonardis, A.[Aleš],
Robust recognition and pose determination of 3-D objects using range images in eigenspace approach,
3DIM01(171-178).
IEEE DOI 0106
BibRef

Franti, P.[Pasi], Virmajoki, O.[Olli], Hautamaki, V.,
Fast Agglomerative Clustering Using a k-Nearest Neighbor Graph,
PAMI(28), No. 11, November 2006, pp. 1875-1881.
IEEE DOI 0609
BibRef

Hautamaki, V.[Ville], Kinnunen, T.[Tomi], Franti, P.[Pasi],
Text-independent speaker recognition using graph matching,
PRL(29), No. 9, 1 July 2008, pp. 1427-1432.
Elsevier DOI 0711
Affine transformation invariance; Graph matching; Structural matching; kNN graph; Clustering; Speaker recognition BibRef

Hillenbrand, U.[Ulrich],
Consistent parameter clustering: Definition and analysis,
PRL(28), No. 9, 1 July 2007, pp. 1112-1122.
Elsevier DOI 0704
Robust estimation; Clustering; Hough transform; Statistical consistency BibRef

Hoseinnezhad, R.[Reza], Bab-Hadiashar, A.[Alireza],
Consistency of robust estimators in multi-structural visual data segmentation,
PR(40), No. 12, December 2007, pp. 3677-3690.
Elsevier DOI 0709
BibRef
And:
A Novel High Breakdown M-estimator for Visual Data Segmentation,
ICCV07(1-6).
IEEE DOI 0710
Robust scale estimation; Robust model fitting; Consistent estimators BibRef

Hoseinnezhad, R.[Reza], Bab-Hadiashar, A.[Alireza],
An M-estimator for high breakdown robust estimation in computer vision,
CVIU(115), No. 8, August 2011, pp. 1145-1156.
Elsevier DOI 1101
Image segmentation; Image motion analysis; Optimization methods; Parameter estimation BibRef

Bab-Hadiashar, A.[Alireza], Hoseinnezhad, R.[Reza],
Bridging Parameter and Data Spaces for Fast Robust Estimation in Computer Vision,
DICTA08(1-8).
IEEE DOI 0812
BibRef

Hoseinnezhad, R.[Reza], Bab-Hadiashar, A.[Alireza],
Multi-Bernoulli sample consensus for simultaneous robust fitting of multiple structures in machine vision,
SIViP(9), No. 7, October 2015, pp. 1727-1736.
WWW Link. 1509
BibRef

Teng, F.[Fei], Chen, Y.X.[Yi-Xin], Dang, X.[Xin],
Multiclass classification with potential function rules: Margin distribution and generalization,
PR(45), No. 1, 2012, pp. 540-551.
Elsevier DOI 1410
Multiclass classification BibRef

Polikar, R.[Robi], DePasquale, J.[Joseph], Mohammed, H.S.[Hussein Syed], Brown, G.[Gavin], Kuncheva, L.I.[Ludmilla I.],
Learn++.MF: A random subspace approach for the missing feature problem,
PR(43), No. 11, November 2010, pp. 3817-3832.
Elsevier DOI 1008
Missing data; Missing features; Ensemble of classifiers; Random subspace method BibRef

Masnadi-Shirazi, H.[Hamed], Vasconcelos, N.M.[Nuno M.],
Cost-Sensitive Boosting,
PAMI(33), No. 2, February 2011, pp. 294-309.
IEEE DOI 1101
losses minimized, emphaxize neighborhood of target boundary. BibRef

Masnadi-Shirazi, H.[Hamed], Mahadevan, V.[Vijay], Vasconcelos, N.M.[Nuno M.],
On the design of robust classifiers for computer vision,
CVPR10(779-786).
IEEE DOI Video of talk:
WWW Link. 1006
BibRef

Bhattacharyya, R.[Ramkishore],
Isolating top-k dense regions with filtration of sparse background,
PRL(32), No. 13, 1 October 2011, pp. 1554-1563.
Elsevier DOI 1109
Cohesion; Core clustering; Cohesive clusters; Top-k clustering Find the optimal subset of points that cluster properly. BibRef

Yu, J.[Jun], Lin, F.[Feng], Seah, H.S.[Hock-Soon], Li, C.H.[Cui-Hua], Lin, Z.Y.[Zi-Yu],
Image classification by multimodal subspace learning,
PRL(33), No. 9, 1 July 2012, pp. 1196-1204.
Elsevier DOI 1202
Subspace; Image classification; Semi-supervised learning; Multimodality BibRef

Kalina, J.[Jan],
Implicitly Weighted Methods in Robust Image Analysis,
JMIV(44), No. 3, November 2012, pp. 449-462.
WWW Link. 1209
BibRef

Ma, J.Y.[Jia-Yi], Zhao, J.[Ji], Tian, J.W.[Jin-Wen], Bai, X.[Xiang], Tu, Z.W.[Zhuo-Wen],
Regularized vector field learning with sparse approximation for mismatch removal,
PR(46), No. 12, 2013, pp. 3519-3532.
Elsevier DOI 1308
Vector field learning BibRef

Zhong, F.J.[Fu-Jin], Li, D.F.[De-Fang], Zhang, J.S.[Jia-Shu],
Robust locality preserving projection based on maximum correntropy criterion,
JVCIR(25), No. 7, 2014, pp. 1676-1685.
Elsevier DOI 1410
Locality preserving projections BibRef

Deng, Y.[Yue], Bao, F.[Feng], Deng, X.S.[Xue-Song], Wang, R.P.[Rui-Ping], Kong, Y.Y.[You-Yong], Dai, Q.H.[Qiong-Hai],
Deep and Structured Robust Information Theoretic Learning for Image Analysis,
IP(25), No. 9, September 2016, pp. 4209-4221.
IEEE DOI 1609
biological tissues BibRef

Li, J.Y.[Jia-Yuan], Hu, Q.W.[Qing-Wu], Ai, M.Y.[Ming-Yao], Zhong, R.F.[Ruo-Fei],
Robust feature matching via support-line voting and affine-invariant ratios,
PandRS(132), No. 1, 2017, pp. 61-76.
Elsevier DOI 1710
Robust feature matching BibRef

Li, Y.Q.[Ye-Qing], Chen, C.[Chen], Yang, F.[Fei], Huang, J.Z.[Jun-Zhou],
Hierarchical Sparse Representation for Robust Image Registration,
PAMI(40), No. 9, September 2018, pp. 2151-2164.
IEEE DOI 1808
BibRef
Earlier:
Deep sparse representation for robust image registration,
CVPR15(4894-4901)
IEEE DOI 1510
BibRef
And: A1, A2, A4, Only:
Transformation-Invariant Collaborative Sub-representation,
ICPR14(3738-3743)
IEEE DOI 1412
Robustness, TV, Image registration, Tensile stress, Distortion, Distortion measurement, Feature extraction, Image registration, sparse learning. Accuracy BibRef

Wang, Y.L.[Yu-Long], Tang, Y.Y.[Yuan Yan], Li, L.Q.[Luo-Qing], Zheng, X.W.[Xian-Wei],
Block sparse representation for pattern classification: Theory, extensions and applications,
PR(88), 2019, pp. 198-209.
Elsevier DOI 1901
Representation based classifier, Block sparsity, Subspace, M-estimator BibRef

Wang, Y.L.[Yu-Long], Tang, Y.Y.[Yuan Yan], Li, L.Q.[Luo-Qing], Wang, P.[Patrick],
Information-theoretic atomic representation for robust pattern classification,
ICPR16(3685-3690)
IEEE DOI 1705
Computational modeling, Databases, Face recognition, Robustness, Training, data BibRef

Ye, X.L.[Xu-Lun], Zhao, J.Y.[Jie-Yu],
Multi-manifold clustering: A graph-constrained deep nonparametric method,
PR(93), 2019, pp. 215-227.
Elsevier DOI 1906
Multi-manifold clustering, Image generation, Dirichlet process mixture model, Variational inference, Graph, Deep neural network BibRef

Liang, Z.Z.[Zhi-Zheng], Chen, X.W.[Xue-Wen], Zhang, L.[Lei], Liu, J.[Jin], Zhou, Y.[Yong],
Correlation classifiers based on data perturbation: New formulations and algorithms,
PR(100), 2020, pp. 107106.
Elsevier DOI 2005
Correlation classifiers, data perturbation, divergence, PMMO, Data classification BibRef

Zhang, X., Liu, C., Suen, C.Y.,
Towards Robust Pattern Recognition: A Review,
PIEEE(108), No. 6, June 2020, pp. 894-922.
IEEE DOI 2006
Pattern recognition, Robustness, Task analysis, Neural networks, Distributed control, Big Data, Machine intelligence, robust pattern recognition BibRef

Li, J., Zhang, J., Pang, N., Qin, X.,
Weighted Outlier Detection of High-Dimensional Categorical Data Using Feature Grouping,
SMCS(50), No. 11, November 2020, pp. 4295-4308.
IEEE DOI 1806
Feature extraction, Anomaly detection, Correlation, Machine learning algorithms, Clustering algorithms, Entropy, outlier detection BibRef

Zhang, M.H.[Miao-Hua], Gao, Y.S.[Yong-Sheng], Zhou, J.[Jun],
A unified weight learning and low-rank regression model for robust complex error modeling,
PR(120), 2021, pp. 108147.
Elsevier DOI 2109
Regression, Weight learning, Low-rank approximation, Generalized correntropy, Robust learning BibRef

Li, Y.M.[Yi-Ming], Wu, B.Y.[Bao-Yuan], Feng, Y.[Yan], Fan, Y.B.[Yan-Bo], Jiang, Y.[Yong], Li, Z.F.[Zhi-Feng], Xia, S.T.[Shu-Tao],
Semi-supervised robust training with generalized perturbed neighborhood,
PR(124), 2022, pp. 108472.
Elsevier DOI 2203
Adversarial Defense, Adversarial Learning, Semi-supervised Learning, AI Security, Deep Learning, Classification BibRef

Xu, Q.Q.[Qian-Qian], Yang, Z.Y.[Zhi-Yong], Jiang, Y.B.[Yang-Bangyan], Cao, X.C.[Xiao-Chun], Yao, Y.[Yuan], Huang, Q.M.[Qing-Ming],
Not All Samples are Trustworthy: Towards Deep Robust SVP Prediction,
PAMI(44), No. 6, June 2022, pp. 3154-3169.
IEEE DOI 2205
Noise measurement, Annotations, Task analysis, Predictive models, Robustness, Visualization, Training, probabilistic model BibRef

Wei, J.F.[Jie-Fei], Meng, Q.G.[Qing-Gang], Yao, L.[Luyan],
Self-Adaptive Logit Balancing for Deep Learning Robustness in Computer Vision,
CIAP22(I:548-559).
Springer DOI 2205
BibRef

Zhang, X.[Xue], Sheng, Z.[Zehua], Shen, H.L.[Hui-Liang],
FocusNet: Classifying better by focusing on confusing classes,
PR(129), 2022, pp. 108709.
Elsevier DOI 2206
Image classification, Inter-class correlations, Confusing classes BibRef

Srivastava, A.[Amber], Velicheti, R.K.[Raj K.], Salapaka, S.M.[Srinivasa M.],
On the choice of number of superstates in the aggregation of Markov chains,
PRL(159), 2022, pp. 181-188.
Elsevier DOI 2206
BibRef

Liu, C.[Cheng], Wang, T.[Tong], Liu, K.[Kun], Zhang, X.Y.[Xin-Ying],
A Novel Sparse Bayesian Space-Time Adaptive Processing Algorithm to Mitigate Off-Grid Effects,
RS(14), No. 16, 2022, pp. xx-yy.
DOI Link 2208
BibRef

Barath, D.[Daniel], Noskova, J.[Jana], Matas, J.G.[Jiri G.],
Marginalizing Sample Consensus,
PAMI(44), No. 11, November 2022, pp. 8420-8432.
IEEE DOI 2210
Data models, Estimation, Adaptation models, Optimization, Computational modeling, Upper bound, Testing, marginalization BibRef

Baráth, D., Noskova, J., Ivashechkin, M., Matas, J.G.,
MAGSAC++, a Fast, Reliable and Accurate Robust Estimator,
CVPR20(1301-1309)
IEEE DOI 2008
Robustness, Data models, Estimation, Noise level, Pattern recognition, Kernel BibRef

He, J.C.[Jia-Cheng], Wang, G.[Gang], Cao, K.[Kui], Diao, H.[He], Wang, G.[Guotai], Peng, B.[Bei],
Generalized minimum error entropy for robust learning,
PR(135), 2023, pp. 109188.
Elsevier DOI 2212
Generalized Gaussian density, Generalized error entropy, Quantized generalized error entropy, Adaptive filtering, Multilayer perceptron BibRef

Truong, G.[Giang], Le, H.[Huu], Zhang, E.[Erchuan], Suter, D.[David], Gilani, S.Z.[Syed Zulqarnain],
Unsupervised Learning for Maximum Consensus Robust Fitting: A Reinforcement Learning Approach,
PAMI(45), No. 3, March 2023, pp. 3890-3903.
IEEE DOI 2302
BibRef
Earlier: A1, A3, A4, A3, A5:
Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach,
CVPR21(10343-10352)
IEEE DOI 2111
Fitting, Unsupervised learning, Computational modeling, Q-learning, Encoding, Task analysis, Maximum consensus, robust fitting, reinforcement learning. Structure from motion, Estimation, Training data. BibRef

Pellegrino, N.[Nicholas], Fieguth, P.W.[Paul W.], Reza, P.H.[Parsin Haji],
K-Means for noise-insensitive multi-dimensional feature learning,
PRL(170), 2023, pp. 113-120.
Elsevier DOI 2306
Feature learning, Clustering, Photoacoustic remote sensing BibRef

Han, X.Z.[Xin-Zhe], Wang, S.H.[Shu-Hui], Su, C.[Chi], Huang, Q.M.[Qing-Ming], Tian, Q.[Qi],
General Greedy De-Bias Learning,
PAMI(45), No. 8, August 2023, pp. 9789-9805.
IEEE DOI 2307
Task analysis, Correlation, Training, Data models, Question answering (information retrieval), Visualization, robust learning BibRef

Dolatabadi, H.M.[Hadi M.], Erfani, S.M.[Sarah M.], Leckie, C.[Christopher],
Adversarial Coreset Selection for Efficient Robust Training,
IJCV(131), No. 12, December 2023, pp. 3307-3331.
Springer DOI 2311
BibRef


Yucel, M.K.[Mehmet Kerim], Cinbis, R.G.[Ramazan Gokberk], Duygulu, P.[Pinar],
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness,
ICCV23(5695-5705)
IEEE DOI 2401
BibRef

Bu, Q.W.[Qing-Wen], Huang, D.[Dong], Cui, H.M.[He-Ming],
Towards Building More Robust Models with Frequency Bias,
ICCV23(4379-4388)
IEEE DOI 2401
BibRef

Hong, H.[Hanbin], Wang, B.H.[Bing-Hui], Hong, Y.[Yuan],
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing,
ECCV22(V:86-103).
Springer DOI 2211
BibRef

Wei, X.[Xian], Xu, Y.[Yangyu], Huang, Y.H.[Yan-Hui], Lv, H.R.[Hai-Rong], Lan, H.[Hai], Chen, M.S.[Ming-Song], Tang, X.[Xuan],
Learning Extremely Lightweight and Robust Model with Differentiable Constraints on Sparsity and Condition Number,
ECCV22(IV:690-707).
Springer DOI 2211
BibRef

Paul, W.[William], Burlina, P.[Philippe],
Robustness and Adaptation to Hidden Factors of Variation,
ArtOfRobust22(122-129)
IEEE DOI 2210
Measurement, Semantics, Robustness, Data models, Pattern recognition BibRef

Wang, Z.Q.[Zi-Qi], Loog, M.[Marco],
Enhancing Classifier Conservativeness and Robustness by Polynomiality,
CVPR22(13317-13326)
IEEE DOI 2210
Deep learning, Computational modeling, Neural networks, Training data, Tail, Robustness, Transfer/low-shot/long-tail learning BibRef

Saikia, T.[Tonmoy], Schmid, C.[Cordelia], Brox, T.[Thomas],
Improving robustness against common corruptions with frequency biased models,
ICCV21(10191-10200)
IEEE DOI 2203
Training, TV, Image coding, Convolution, Object detection, Distortion, Representation learning, BibRef

Yeo, T.[Teresa], Kar, O.F.[Oguzhan Fatih], Zamir, A.[Amir],
Robustness via Cross-Domain Ensembles,
ICCV21(12169-12179)
IEEE DOI 2203
Uncertainty, Neural networks, Merging, Training data, Robustness, Task analysis, Machine learning architectures and formulations, Scene analysis and understanding BibRef

Liu, H.Z.[Hao-Zhe], Wu, H.Q.[Hao-Qian], Xie, W.C.[Wei-Cheng], Liu, F.[Feng], Shen, L.L.[Lin-Lin],
Group-wise Inhibition based Feature Regularization for Robust Classification,
ICCV21(468-476)
IEEE DOI 2203
Training, Codes, Heuristic algorithms, Robustness, Classification algorithms, Convolutional neural networks, Representation learning BibRef

Yuan, S.Y.[Si-Yang], Li, Y.T.[Yi-Tong], Wang, D.[Dong], Bai, K.[Ke], Carin, L.[Lawrence], Carlson, D.[David],
Learning to Weight Filter Groups for Robust Classification,
WACV22(3321-3330)
IEEE DOI 2202
Training, Neural networks, Training data, Data visualization, Big Data, Benchmark testing, Deep Learning Object Detection/Recognition/Categorization BibRef

Sarkar, A.[Anindya], Sarkar, A.[Anirban], Balasubramanian, V.N.[Vineeth N.],
Leveraging Test-Time Consensus Prediction for Robustness against Unseen Noise,
WACV22(3564-3573)
IEEE DOI 2202
Training, Representation learning, Gaussian noise, Speckle, Predictive models, Robustness, Deep Learning -> Efficient Training and Inference Methods for Networks Vision Systems and Applications BibRef

Ibrahimi, S.[Sarah], Sors, A.[Arnaud], de Rezende, R.S.[Rafael Sampaio], Clinchant, S.[Stéphane],
Learning with Label Noise for Image Retrieval by Selecting Interactions,
WACV22(468-477)
IEEE DOI 2202
Training, Image retrieval, Benchmark testing, Noise measurement, Image classification, Learning and Optimization BibRef

Go, H.[Hyojun], Byun, J.[Junyoung], Kim, C.[Changick],
Rethinking Training Schedules for Verifiably Robust Networks,
ICIP21(464-468)
IEEE DOI 2201
Training, Deep learning, Schedules, Analytical models, Perturbation methods, Image processing, Adversarial robustness BibRef

Lakshya, L.[Lakshya],
Behaviour of Sample Selection Techniques Under Explicit Regularization,
ISVC21(I:331-340).
Springer DOI 2112
BibRef

Chang, C.H.[Chun-Hao], Adam, G.A.[George Alexandru], Goldenberg, A.[Anna],
Towards Robust Classification Model by Counterfactual and Invariant Data Generation,
CVPR21(15207-15216)
IEEE DOI 2111
Industries, Correlation, Image recognition, Annotations, Computational modeling, Machine learning BibRef

Ortego, D.[Diego], Arazo, E.[Eric], Albert, P.[Paul], O'Connor, N.E.[Noel E.], McGuinness, K.[Kevin],
Multi-Objective Interpolation Training for Robustness to Label Noise,
CVPR21(6602-6611)
IEEE DOI 2111
Training, Deep learning, Interpolation, Prototypes, Robustness, Noise robustness, Pattern recognition BibRef

Qu, Y.T.[Yun-Tao], Mo, S.S.[Sha-Sha], Niu, J.W.[Jian-Wei],
DAT: Training Deep Networks Robust to Label-Noise by Matching the Feature Distributions,
CVPR21(6817-6825)
IEEE DOI 2111
Training, Codes, Feature extraction, Extraterrestrial measurements, Generators, Pattern recognition BibRef

Cazenavette, G.[George], Murdock, C.[Calvin], Lucey, S.[Simon],
Architectural Adversarial Robustness: The Case for Deep Pursuit,
CVPR21(7146-7154)
IEEE DOI 2111
Deep learning, Resistance, Sensitivity, Sparse representation, Robustness BibRef

Awasthi, P.[Pranjal], Yu, G.[George], Ferng, C.S.[Chun-Sung], Tomkins, A.[Andrew], Juan, D.C.[Da-Cheng],
Adversarial Robustness Across Representation Spaces,
CVPR21(7604-7612)
IEEE DOI 2111
Training, Deep learning, Perturbation methods, Neural networks, Robustness, Pattern recognition BibRef

Nam, H.[Hyeonseob], Lee, H.J.[Hyun-Jae], Park, J.[Jongchan], Yoon, W.J.[Won-Jun], Yoo, D.G.[Dong-Geun],
Reducing Domain Gap by Reducing Style Bias,
CVPR21(8686-8695)
IEEE DOI 2111
Adaptation models, Shape, Decision making, Aerospace electronics, Robustness, Encoding BibRef

Zhang, H.Y.[Hai-Yang], Xing, X.M.[Xi-Ming], Liu, L.[Liang],
DualGraph: A graph-based method for reasoning about label noise,
CVPR21(9649-9658)
IEEE DOI 2111
Training, Recurrent neural networks, Reliability engineering, Graph neural networks, Robustness, Pattern recognition BibRef

Mackowiak, R.[Radek], Ardizzone, L.[Lynton], Köthe, U.[Ullrich], Rother, C.[Carsten],
Generative Classifiers as a Basis for Trustworthy Image Classification,
CVPR21(2970-2980)
IEEE DOI 2111
Training, Deep learning, Computational modeling, Robustness, Pattern recognition BibRef

Burns, C.[Collin], Steinhardt, J.[Jacob],
Limitations of Post-Hoc Feature Alignment for Robustness,
CVPR21(2525-2533)
IEEE DOI 2111
To improve robustness. Training, Knowledge engineering, Neural networks, Buildings, Benchmark testing, Robustness BibRef

Collier, M.[Mark], Mustafa, B.[Basil], Kokiopoulou, E.[Efi], Jenatton, R.[Rodolphe], Berent, J.[Jesse],
Correlated Input-Dependent Label Noise in Large-Scale Image Classification,
CVPR21(1551-1560)
IEEE DOI 2111
Training, Correlation, Uncertainty, Neural networks, Estimation, Probabilistic logic, Pattern recognition BibRef

Serrurier, M.[Mathieu], Mamalet, F.[Franck], González-Sanz, A.[Alberto], Boissin, T.[Thibaut], Loubes, J.M.[Jean-Michel], del Barrio, E.[Eustasio],
Achieving robustness in classification using optimal transport with hinge regularization,
CVPR21(505-514)
IEEE DOI 2111
Computational modeling, Transportation, Estimation, Fasteners, Robustness, Pattern recognition BibRef

Shibzukhov, Z.M.[Zaur M.], Semenov, T.A.[Timofey A.],
Machine Learning Based on Minimizing Robust Mean Estimates,
IMTA20(112-119).
Springer DOI 2103
BibRef

Li, A.[Ao], Chen, J.J.[Jia-Jia], Chen, D.[Deyun], Sun, G.L.[Guang-Lu],
Multiview Similarity Learning for Robust Visual Clustering,
MMHUA20(168-183).
Springer DOI 2103
BibRef

Sun, G.[Guolei], Khan, S.[Salman], Li, W.[Wen], Cholakkal, H.[Hisham], Khan, F.S.[Fahad Shahbaz], Van Gool, L.J.[Luc J.],
Fixing Localization Errors to Improve Image Classification,
ECCV20(XXV:271-287).
Springer DOI 2011
BibRef

Peng, X.J.[Xiao-Jiang], Wang, K.[Kai], Zeng, Z.Y.[Zhao-Yang], Li, Q.[Qing], Yang, J.F.[Jian-Fei], Qiao, Y.[Yu],
Suppressing Mislabeled Data via Grouping and Self-attention,
ECCV20(XVI: 786-802).
Springer DOI 2010
BibRef

Sarhan, M.H.[Mhd Hasan], Navab, N.[Nassir], Eslami, A.[Abouzar], Albarqouni, S.[Shadi],
Fairness by Learning Orthogonal Disentangled Representations,
ECCV20(XXIX: 746-761).
Springer DOI 2010
BibRef

Hayes, J.[Jamie],
Extensions and limitations of randomized smoothing for robustness guarantees,
AML-CV20(3413-3421)
IEEE DOI 2008
Smoothing methods, Robustness, Perturbation methods, Random variables, Visualization BibRef

Li, Y., Vasconcelos, N.M.[Nuno M.],
Background Data Resampling for Outlier-Aware Classification,
CVPR20(13215-13224)
IEEE DOI 2008
Training, Data models, Image recognition, Task analysis, Standards, Entropy, Computational complexity BibRef

Laugros, A., Caplier, A., Ospici, M.,
Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?,
RLQ19(1045-1054)
IEEE DOI 2004
neural nets, perturbation techniques, robust control, adversarial robustness, adversarial examples study, Adversarial Examples BibRef

Huang, W.[Wei], Yue, X.D.[Xiao-Dong], Zhong, C.M.[Cai-Ming], Zhang, N.[Nan],
Rough Neighborhood Covering Reduction for robust classification,
ICPR16(3308-3313)
IEEE DOI 1705
Algorithm design and analysis, Approximation algorithms, Classification algorithms, Data models, Robustness, Rough sets, Uncertainty BibRef

Vinh, N.X.[Nguyen Xuan], Erfani, S., Paisitkriangkrai, S., Bailey, J., Leckie, C., Ramamohanarao, K.,
Training robust models using Random Projection,
ICPR16(531-536)
IEEE DOI 1705
Artificial neural networks, Data models, Learning systems, Robustness, Training, Training data BibRef

Hou, J.[Jian], E, X.[Xu], Chi, L.[Lei], Xia, Q.[Qi], Qi, N.M.[Nai-Ming],
Robust Clustering Based on Dominant Sets,
ICPR14(1466-1471)
IEEE DOI 1412
Clustering algorithms BibRef

Hou, J.[Jian], Xu, E., Chi, L.[Lei], Xia, Q.[Qi], Qi, N.M.[Nai-Ming],
DSET: A robust clustering algorithm,
ICIP13(3795-3799)
IEEE DOI 1402
clustering BibRef

Huang, D.[Dong], Cabral, R.S.[Ricardo Silveira], de la Torre, F.[Fernando],
Robust Regression,
ECCV12(IV: 616-630).
Springer DOI 1210
BibRef

Lu, C.Y.[Can-Yi], Min, H.[Hai], Zhao, Z.Q.[Zhong-Qiu], Zhu, L.[Lin], Huang, D.S.[De-Shuang], Yan, S.C.[Shui-Cheng],
Robust and Efficient Subspace Segmentation via Least Squares Regression,
ECCV12(VII: 347-360).
Springer DOI 1210
BibRef

Evans, H., Zhang, M.,
Particle swarm optimisation for object classification,
IVCNZ08(1-6).
IEEE DOI 0811
BibRef

Bauckhage, C.[Christian],
Probabilistic Diffusion Classifiers for Object Detection,
ICPR08(1-4).
IEEE DOI 0812
BibRef
Earlier:
Robust Tensor Classifiers for Color Object Recognition,
ICIAR07(352-363).
Springer DOI 0708
BibRef

Raducanu, B.[Bogdan], Vitriŕ, J.[Jordi],
Incremental Subspace Learning for Cognitive Visual Processes,
BVAI07(214-223).
Springer DOI 0710
BibRef

Ferraz, L., Felip, R., Martínez, B., Binefa, X.,
A Density-Based Data Reduction Algorithm for Robust Estimators,
IbPRIA07(II: 355-362).
Springer DOI 0706
BibRef

Xiong, L.[Liang], Li, J.G.[Jian-Guo], Zhang, C.S.[Chang-Shui],
Discriminant Additive Tangent Spaces for Object Recognition,
CVPR07(1-8).
IEEE DOI 0706
BibRef

Khurd, P.[Parmeshwar], Baloch, S.H.[Sajjad H.], Gur, R.[Ruben], Davatzikos, C.[Christos], Verma, R.[Ragini],
Manifold Learning Techniques in Image Analysis of High-dimensional Diffusion Tensor Magnetic Resonance Images,
ComponentAnalysis07(1-7).
IEEE DOI 0706
BibRef

Duin, R.P.W.[Robert P. W.], Fred, A.L.N.[Ana L.N.], Loog, M.[Marco], Pekalska, E.[El˙zbieta],
Mode Seeking Clustering by KNN and Mean Shift Evaluated,
SSSPR12(51-59).
Springer DOI 1211
BibRef

Zheng, W.M.[Wen-Ming], Tang, X.[Xiaoou],
A Robust Algorithm for Generalized Orthonormal Discriminant Vectors,
ICPR06(II: 784-787).
IEEE DOI 0609
BibRef

Felsberg, M.[Michael], Granlund, G.H.[Gosta H.],
P-Channels: Robust Multivariate M-Estimation of Large Datasets,
ICPR06(III: 262-267).
IEEE DOI 0609
BibRef

Yang, F.W.[Fu-Wen], Lin, H.J.[Hwei-Jen], Wang, P.S.P.[Patrick S. P.], Wu, H.H.[Hung-Hsuan],
Robust Clustering based on Winner-Population Markov Chain,
ICPR06(II: 589-592).
IEEE DOI 0609
BibRef

Cao, W.B.[Wen-Bo], Haralick, R.M.[Robert M.],
Nonlinear Manifold Clustering By Dimensionality,
ICPR06(I: 920-924).
IEEE DOI 0609
BibRef

Hou, X.W.[Xin-Wen], Liu, C.L.[Cheng-Lin], Tan, T.N.[Tie-Niu],
Learning Boosted Asymmetric Classifiers for Object Detection,
CVPR06(I: 330-338).
IEEE DOI 0606
BibRef

Kaufhold, J.[John], Abbott, J.[Justin], Kaucic, R.[Robert],
Distributed Cost Boosting and Bounds on Mis-classification Cost,
CVPR06(I: 146-153).
IEEE DOI 0606
Cost sensitive boosting for industrial applications. BibRef

Yan, W.[Wang], Liu, Q.S.[Qing-Shan], Lu, H.Q.[Han-Qing], Ma, S.D.[Song-De],
Multiple Similarities Based Kernel Subspace Learning for Image Classification,
ACCV06(II:244-253).
Springer DOI 0601
BibRef

Grossmann, E.[Etienne],
AdaTree: Boosting a Weak Classifier into a Decision Tree,
LCV04(105).
IEEE DOI 0406
BibRef

Souvenir, R.[Richard], Pless, R.[Robert],
Manifold Clustering,
ICCV05(I: 648-653).
IEEE DOI 0510
Separating intersecting classes. BibRef

Herbin, S.,
Robust multihypothesis discrimination of controlled I.I.D. processes,
ICPR04(I: 200-203).
IEEE DOI 0409
BibRef

Chen, H.F.[Hai-Feng], Shimshoni, I., Meer, P.,
Model based object recognition by robust information fusion,
ICPR04(III: 57-60).
IEEE DOI 0409
BibRef

Ying, Z.[Zhao], Keong, K.C.[Kwoh Chee],
Fast leave-one-out evaluation and improvement on inference for LS-SVMs,
ICPR04(III: 494-497).
IEEE DOI 0409
BibRef

Chen, H.F.[Hai-Feng], Meer, P.,
Robust regression with projection based m-estimators,
ICCV03(878-885).
IEEE DOI 0311
BibRef

Lepetit, V., Shahrokni, A., Fua, P.,
Robust data association for online applications,
CVPR03(I: 281-288).
IEEE DOI 0307
BibRef

Choukroun, A.[Ariel], Charvillat, V.[Vincent],
Bucketing Techniques in Robust Regression for Computer Vision,
SCIA03(609-616).
Springer DOI 0310
BibRef

Ben Hamza, A.[Abdessamad], Krim, H.,
Robust influence functionals for image filtering,
ICIP03(III: 361-364).
IEEE DOI 0312

See also Geodesic Matching of Triangulated Surfaces. BibRef

Izquierdo, E.[Ebroul],
A Highly Robust Regressor and its Application in Computer Vision,
BMVC00(xx-yy).
PDF File. 0009
BibRef

Myatt, D.R., Torr, P.H.S.[Philip H.S.], Nasuto, S.J., Bishop, J.M., Craddock, R.,
NAPSAC: High Noise, High Dimensional Robust Estimation - it's in the Bag,
BMVC02(Computer Vision Tools). 0208
BibRef

Comby, F.[Frederic], Strauss, O.[Olivier], Aldon, M.J.[Marie-José],
Possibility Theory and Rough Histograms for Motion Estimation in a Video Sequence,
VF01(473 ff.).
Springer DOI 0209
BibRef

Strauss, O., Comby, F., Aldon, M.J.,
Rough Histograms for Robust Statistics,
ICPR00(Vol II: 684-687).
IEEE DOI 0009
BibRef

Barakat, H., Blostein, D.,
Training with positive and negative data samples: Effects on a classifier for hand-drawn geometric shapes,
ICDAR01(1017-1021).
IEEE DOI 0109
BibRef

Ohya, J., Sengupta, K.,
Generating Virtual Environments for Human Communications: Virtual Metamorphosis System and Novel View Generation,
CVVRHC98(Sensing and Rendering Real Scenes). BibRef 9800

Bischof, H.[Horst], Leonardis, A.[Ales], Pezzei, F.[Florian],
A Robust Subspace Classifier,
ICPR98(Vol I: 114-116).
IEEE DOI 9808
BibRef

Schunck, B.G.[Brian G.],
Robust Computational Vision,
Robust90(xx). BibRef 9000

Zhuang, X.H.[Xin-Hua], and Haralick, R.M.[Robert M.],
Developing Robust Techniques for Computer Vision,
Robust90(xx). BibRef 9000

Chen, C.H.[Chien-Huei], and Mulgaonkar, P.G.[Prasanna G.],
Robust Vision-Programs Based on Statistical Feature Measurements,
Robust90(xx). BibRef 9000

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Noisy Labels for Learning .


Last update:Mar 16, 2024 at 20:36:19