14.5.10.2 Neural Networks Combinations and Evaluations

Chapter Contents (Back)
Evaluation, Neural Networks. Neural Networks.
See also Recurrent Neural Networks for Shapes and Complex Features, RNN.

Hansen, L.K., Salamon, P.,
Neural network ensembles,
PAMI(12), No. 10, October 1990, pp. 993-1001.
IEEE DOI 0401
BibRef

Bourlard, H., Wellekens, C.J.,
Links between Markov models and multilayer perceptrons,
PAMI(12), No. 12, December 1990, pp. 1167-1178.
IEEE DOI 0401
BibRef

Fu, L.M.[Li-Min],
Analysis of the dimensionality of neural networks for pattern recognition,
PR(23), No. 10, 1990, pp. 1131-1140.
Elsevier DOI 0401
BibRef

Musavi, M.T., Chan, K.H., Hummels, D.M., Kalantri, K., Ahmed, W.,
A probabilistic model for evaluation of neural network classifiers,
PR(25), No. 10, October 1992, pp. 1241-1251.
Elsevier DOI 0401
BibRef

Ruck, D.W., Rogers, S.K., Kabrisky, M., Maybeck, P.S., Oxley, M.E.,
Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons,
PAMI(14), No. 6, June 1992, pp. 686-691.
IEEE DOI 0401
BibRef

Schmidt, W.A.C., Davis, J.P.,
Pattern recognition properties of various feature spaces for higher order neural networks,
PAMI(15), No. 8, August 1993, pp. 795-801.
IEEE DOI 0401
BibRef

Jou, I.C.[I. Chang], You, S.S.[Shih-Shien], Chang, L.W.[Long-Wen],
Analysis of hidden nodes for multi-layer perceptron neural networks,
PR(27), No. 6, June 1994, pp. 859-864.
Elsevier DOI 0401
BibRef

Hamamoto, Y., Uchimura, S., Tomita, S.,
On the Behavior of Artificial Neural-Network Classifiers in High-Dimensional Spaces,
PAMI(18), No. 5, May 1996, pp. 571-574.
IEEE DOI 9606
Neural Networks. BibRef

Hamamoto, Y., Matsuura, Y., Kanaoka, T., and Tomita, S.,
A Note on the Orthonormal Discriminant Vector Method for Feature Extraction,
PR(24), No. 7, 1991, pp. 681-684.
Elsevier DOI BibRef 9100

Hamamoto, Y.[Yoshihiko], Kanaoka, T.[Taiho], Tomita, S.[Shingo],
On a theoretical comparison between the orthonormal discriminant vector method and discriminant analysis,
PR(26), No. 12, December 1993, pp. 1863-1867.
Elsevier DOI 0401
BibRef
Earlier:
Orthogonal discriminant analysis for interactive pattern analysis,
ICPR90(I: 424-427).
IEEE DOI 9006
BibRef

Hamamoto, Y., Ohama, A., Kanaoka, T., Tomita, S.,
Orthogonal discriminant analysis based on a modified Fisher criterion,
ICPR92(II:363-366).
IEEE DOI 9208
feature extraction BibRef

Archer, N.P., Wang, S.,
Learning bias in neural networks and an approach to controlling its effect in monotonic classification,
PAMI(15), No. 9, September 1993, pp. 962-966.
IEEE DOI 0401
BibRef

Park, Y.T.[Young-Tae],
A comparison of neural net classifiers and linear tree classifiers: Their similarities and differences,
PR(27), No. 11, November 1994, pp. 1493-1503.
Elsevier DOI 0401
BibRef

Sarat Chandran, P.,
Comments on 'Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons',
PAMI(16), No. 8, August 1994, pp. 862-863.
IEEE DOI 0401

See also Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons. BibRef

Cho, S.B., Kim, J.H.,
Combining Multiple Neural Networks by Fuzzy Integral for Robust Classification,
SMC(25), No. 2, 1995, pp. 380-384. BibRef 9500

Cho, S.B., Kim, J.H.,
Multiple Network Fusion Using Fuzzy Logic,
TNN(6), No. 2, 1995, pp. 497-501. BibRef 9500

Hashem, Schmeiser, B.,
Improving Model Accuracy Using Optimal Linear Combinations of Trained Neural Networks,
TNN(6), No. 3, 1995, pp. 792-794. BibRef 9500

Chong, C.C., Jia, J.C.,
Assessments of Neural-Network Classifier Output Codings Using Variability of Hamming Distance,
PRL(17), No. 8, July 1 1996, pp. 811-818. 9608
BibRef
Earlier:
Assessments of neural network output codings for classification of multispectral images using Hamming distance measure,
ICPR94(B:526-528).
IEEE DOI 9410
BibRef

Kanellopoulos, I., Wilkinson, G.G.,
Strategies and Best Practice for Neural-Network Image Classification,
JRS(18), No. 4, March 10 1997, pp. 711-725. 9703
BibRef

Holmstrom, L., Koistinen, P., Laaksonen, J.T.[Jorma T.], Oja, E.,
Neural and Statistical Classifiers: Taxonomy and Two Case-Studies,
TNN(8), No. 1, January 1997, pp. 5-17. 9701
BibRef
Earlier: A1, A4, A2, A3:
Neural Network and Statistical Perspectives of Classification,
ICPR96(IV: 286-290).
IEEE DOI 9608
(Helsinki Univ. of Technology, SF) BibRef

Guan, L., Anderson, J.A., Sutton, J.P.,
A Network of Networks Processing Model for Image Regularization,
TNN(8), No. 1, January 1997, pp. 169-174. 9701
BibRef

Gao, D.Q.[Da Qi], Wu, S.Y.[Shou Yi],
An Optimization Method for the Topological Structures of Feedforward Multilayer Neural Networks,
PR(31), No. 9, September 1998, pp. 1337-1342.
Elsevier DOI 9808
BibRef

Tang, X.O.,
Multiple Competitive Learning Network Fusion for Object Classification,
SMC-B(28), No. 4, August 1998, pp. 532-543.
IEEE Top Reference. 9808
BibRef

Babri, H.A., Chen, Y.Q., Yin, T.,
Improving Backpropagation Learning Under Limited Precision,
PRL(19), No. 11, September 1998, pp. 1007-1016. 9811
BibRef

Sierra, A., Santa Cruz, C.,
Global and Local Neural-Network Ensembles,
PRL(19), No. 8, June 1998, pp. 651-655. 9808
BibRef

Gori, M., Tesi, A.,
On the problem of local minima in backpropagation,
PAMI(14), No. 1, January 1992, pp. 76-86.
IEEE DOI 0401
BibRef

Venkatesh, S.S., Psaltis, D.,
On reliable computation with formal neurons,
PAMI(14), No. 1, January 1992, pp. 87-91.
IEEE DOI 0401
BibRef

Gori, M.[Marco], Scarselli, F.[Franco],
Are Multilayer Perceptrons Adequate for Pattern-Recognition and Verification,
PAMI(20), No. 11, November 1998, pp. 1121-1132.
IEEE DOI 9811
BibRef

Lerner, B.[Boaz], Guterman, H.[Hugo], Aladjem, M.[Mayer], Dinstein, I.[Its'hak],
Comparative Study of Neural Network Based Feature Extraction Paradigms,
PRL(20), No. 1, January 1999, pp. 7-14. BibRef 9901
Earlier:
Feature Extraction by Neural Network Nonlinear Mapping for Pattern Classification,
ICPR96(IV: 320-324).
IEEE DOI 9608
(Ben-Gurion Univ. IL) BibRef

Serpico, S.B., Bruzzone, L., Roli, F.,
An Experimental Comparison of Neural and Statistical Nonparametric Algorithms for Supervised Classification of Remote Sensing Images,
PRL(17), No. 13, November 25 1996, pp. 1331-1341. 9701
Neural Networks. Comparisons. Remote Sensing. BibRef

Giacinto, G.[Giorgio], Roli, F.[Fabio], Bruzzone, L.[Lorenzo],
Combination of neural and statistical algorithms for supervised classification of remote-sensing images,
PRL(21), No. 5, May 2000, pp. 385-397. 0005

See also approach to the automatic design of multiple classifier systems, An. BibRef

Bruzzone, L., Fernàndez Prieto, D., Serpico, S.B.,
A Neural-Statistical Approach to Multitemporal and Multisource Remote-Sensing Image Classification,
GeoRS(37), No. 3, May 1999, pp. 1350.
IEEE Top Reference. BibRef 9905

Roli, F., Serpico, S., Bruzzone, L.,
Classification of Multisensor Remote Sensing Images by Multiple Structured Neural Networks,
ICPR96(IV: 180-184).
IEEE DOI 9608
(Univ. di Cagliari, I) BibRef

Bruzzone, L., Serpico, S.B.,
Classification of Imbalanced Remote Sensing Data by Neural Networks,
PRL(18), No. 11-13, November 1997, pp. 1323-1328. 9806
BibRef

Bruzzone, L., Fernàndez Prieto, D.,
An incremental-learning neural network for the classification of remote-sensing images,
PRL(20), No. 11-13, November 1999, pp. 1241-1248. 0001
BibRef

Bruzzone, L., Carlin, L.,
A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images,
GeoRS(44), No. 9, September 2006, pp. 2587-2600.
IEEE DOI 0609
BibRef

Perner, P.[Petra], Zscherpel, U.[Uwe], Jacobsen, C.[Carsten],
A comparison between neural networks and decision trees based on data from industrial radiographic testing,
PRL(22), No. 1, January 2001, pp. 47-54.
Elsevier DOI 0105
BibRef

Baraldi, A., Binaghi, E., Blonda, P., Brivio, P.A., Rampini, A.,
Comparison of the multilayer perceptron with neuro-fuzzy techniques in the estimation of cover class mixture in remotely sensed data,
GeoRS(39), No. 5, May 2001, pp. 994-1005.
IEEE Top Reference. 0106
BibRef

Giacinto, G.[Giorgio], Roli, F.[Fabio],
Design of effective neural network ensembles for image classification purposes,
IVC(19), No. 9-10, August 2001, pp. 699-707.
Elsevier DOI 0108

See also Combination of neural and statistical algorithms for supervised classification of remote-sensing images. BibRef

Giacinto, G., Roli, F.[Fabio], Fumera, G.[Giorgio],
Design of Effective Multiple Classifier Systems by Clustering of Classifiers,
ICPR00(Vol II: 160-163).
IEEE DOI 0009
BibRef

Behloul, F., Lelieveldt, B.P.F., Boudraa, A., Reiber, J.H.C.,
Optimal design of radial basis function neural networks for fuzzy-rule extraction in high dimensional data,
PR(35), No. 3, March 2002, pp. 659-675.
Elsevier DOI 0201
BibRef

Woods, K., Bowyer, K.W.,
Generating ROC curves for artificial neural networks,
MedImg(16), No. 3, June 1997, pp. 329-337.
IEEE Top Reference. 0205
BibRef

Racca, R.[Robert],
Can periodic perceptrons replace multi-layer perceptrons?,
PRL(21), No. 12, November 2000, pp. 1019-1025. 0011
BibRef

Pal, N.R., Bezdek, J.C.,
Complexity reduction for 'large image' processing,
SMC-B(32), No. 5, October 2002, pp. 598-611. Sampling method. Train NN or clustering on the samples only.
IEEE Top Reference. 0210
BibRef

Jiang, Y.L.[Yu-Lei],
Uncertainty in the output of artificial neural networks,
MedImg(22), No. 7, July 2003, pp. 913-921.
IEEE Abstract. 0308
BibRef

Weber, K.E.[Karsten E.], Schlagner, W.[Werner], Schweier, K.[Knuth],
Estimating regional noise on neural network predictions,
PR(36No. 10, October 2003, pp. 2333-2337.
Elsevier DOI 0308
BibRef

Gao, D.Q.[Da Qi], Yang, G.X.[Gen-Xing],
Influences of variable scales and activation functions on the performances of multilayer feedforward neural networks,
PR(36), No. 4, April 2003, pp. 869-878.
Elsevier DOI 0304
BibRef

Abbas, H.M.[Hazem M.],
Analysis and pruning of nonlinear auto-association networks,
VISP(151), No. 1, February 2004, pp. 44-50.
IEEE Abstract. 0403
Analysis of Neural networks. BibRef

Abbas, H.M.[Hazem M.],
Classified image compression using optimally structured auto-association networks,
IET-IPR(1), No. 2, June 2007, pp. 189-196.
DOI Link 0905
BibRef

Gao, D.Q.[Da-Qi], Ji, Y.[Yan],
Classification methodologies of multilayer perceptrons with sigmoid activation functions,
PR(38), No. 10, October 2005, pp. 1469-1482.
Elsevier DOI 0508
BibRef

Cantu-Paz, E., Kamath, C.,
An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems,
SMC-B(35), No. 5, October 2005, pp. 915-927.
IEEE DOI 0510
Compares 8 combinations of NN algorithms. BibRef

Hervás-Martínez, C.[César], Martínez-Estudillo, F.[Francisco],
Logistic regression using covariates obtained by product-unit neural network models,
PR(40), No. 1, January 2007, pp. 52-64.
Elsevier DOI 0611
Logistic regression; Product-unit neural network; Classification BibRef

Gao, D.Q.[Da Qi], Li, C.X.[Chun-Xia], Yang, Y.F.[Yun-Fan],
Task decomposition and modular single-hidden-layer perceptron classifiers for multi-class learning problems,
PR(40), No. 8, August 2007, pp. 2226-2236.
Elsevier DOI 0704
Task decomposition; Multi-class learning data sets; Modular multilayer perceptrons; Unbalanced classes; Weak distribution regions; Output amendment BibRef

Kang, S.G.[Sang-Gil], Park, S.J.[Sung-Joon],
A fusion neural network classifier for image classification,
PRL(30), No. 9, 1 July 2009, pp. 789-793.
Elsevier DOI 0905
Image classification; Fusion neural network classifier; Sensitivity; MPEG-7 descriptor BibRef

Quteishat, A., Lim, C.P., Tan, K.S.,
A Modified Fuzzy Min-Max Neural Network With a Genetic-Algorithm-Based Rule Extractor for Pattern Classification,
SMC-A(40), No. 3, May 2010, pp. 641-650.
IEEE DOI 1003
BibRef

Raudys, S.J.[Sarunas J.], Raudys, A.[Aistis],
Pairwise Costs in Multiclass Perceptrons,
PAMI(32), No. 7, July 2010, pp. 1324-1328.
IEEE DOI 1006
Train net of K single layer perceptrons. BibRef

Salas, R.[Rodrigo], Saavedra, C.[Carolina], Allende, H.[Héctor], Moraga, C.,
Machine fusion to enhance the topology preservation of vector quantization artificial neural networks,
PRL(32), No. 7, 1 May 2011, pp. 962-972.
Elsevier DOI 1101
Machine fusion; Topology preservation; Vector quantization artificial neural networks; Machine learning ensembles BibRef

Saavedra, C.[Carolina], Moreno, S.[Sebastián], Salas, R.[Rodrigo], Allende, H.[Héctor],
Robustness Analysis of the Neural Gas Learning Algorithm,
CIARP06(559-568).
Springer DOI 0611
BibRef

Allende-Cid, H.[Héctor], Veloz, A.[Alejandro], Salas, R.[Rodrigo], Chabert, S.[Steren], Allende, H.[Héctor],
Self-Organizing Neuro-Fuzzy Inference System,
CIARP08(429-436).
Springer DOI 0809
BibRef

Lessmann, M.[Markus],
Learning of invariant object recognition in hierarchical neural networks using temporal continuity,
ELCVIA(14), No. 3, 2015, pp. xx-yy.
DOI Link 1601
Thesis summary. BibRef

Nanni, L.[Loris], Ghidoni, S.[Stefano], Brahnam, S.[Sheryl],
Handcrafted vs. non-handcrafted features for computer vision classification,
PR(71), No. 1, 2017, pp. 158-172.
Elsevier DOI 1707
Deep, learning BibRef

Wang, X.G.[Xing-Gang], Yan, Y.L.[Yong-Luan], Tang, P.[Peng], Bai, X.[Xiang], Liu, W.Y.[Wen-Yu],
Revisiting multiple instance neural networks,
PR(74), No. 1, 2018, pp. 15-24.
Elsevier DOI 1711
Multiple instance learning BibRef

Li, J.[Jun], Chang, H.Y.[He-You], Yang, J.[Jian], Luo, W.[Wei], Fu, Y.[Yun],
Visual Representation and Classification by Learning Group Sparse Deep Stacking Network,
IP(27), No. 1, January 2018, pp. 464-476.
IEEE DOI 1712
Biological neural networks, Dictionaries, Encoding, Stacking, Training, Deep learning, image classification, stacking network BibRef

Garcia-Garcia, A.[Alberto], Garcia-Rodriguez, J.[Jose], Orts-Escolano, S.[Sergio], Oprea, S.[Sergiu], Gomez-Donoso, F.[Francisco], Cazorla, M.[Miguel],
A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition,
CVIU(164), No. 1, 2017, pp. 124-134.
Elsevier DOI 1801
Deep learning BibRef

Rao, Y.M.[Yong-Ming], Lu, J.W.[Ji-Wen], Lin, J.[Ji], Zhou, J.[Jie],
Runtime Network Routing for Efficient Image Classification,
PAMI(41), No. 10, October 2019, pp. 2291-2304.
IEEE DOI 1909
Routing, Runtime, Neural networks, Acceleration, Training, Computational modeling, Deep network compression, deep learning BibRef

Wu, Z.S.[Zi-Sheng], Ling, B.W.K.[Bingo Wing-Kuen],
Training algorithm for perceptron with multi-pulse type activation function,
SIViP(14), No. 5, July 2020, pp. 925-933.
Springer DOI 2006
BibRef

Melnykov, V.[Volodymyr], Sarkar, S.[Shuchismita], Melnykov, Y.[Yana],
On finite mixture modeling and model-based clustering of directed weighted multilayer networks,
PR(112), 2021, pp. 107641.
Elsevier DOI 2102
Model-based clustering, Directed network, Weighted network, Multilayer network, MCMC BibRef

Kahatapitiya, K.[Kumara], Rodrigo, R.[Ranga],
Exploiting the Redundancy in Convolutional Filters for Parameter Reduction,
WACV21(1409-1419)
IEEE DOI 2106
Correlation, Computational modeling, Redundancy, Memory management, Network architecture BibRef

Tissera, D.[Dumindu], Vithanage, K.[Kasun], Wijesinghe, R.[Rukshan], Kahatapitiya, K.[Kumara], Fernando, S.[Subha], Rodrigo, R.[Ranga],
Feature-Dependent Cross-Connections in Multi-Path Neural Networks,
ICPR21(4032-4039)
IEEE DOI 2105
Adaptation models, Adaptive systems, Neural networks, Redundancy, Feature extraction, Routing, Complexity theory BibRef

Liu, C.X.[Chun-Xiao], Mao, Z.D.[Zhen-Dong], Zhang, T.Z.[Tian-Zhu], Liu, A.A.[An-An], Wang, B.[Bin], Zhang, Y.D.[Yong-Dong],
Focus Your Attention: A Focal Attention for Multimodal Learning,
MultMed(24), 2022, pp. 103-115.
IEEE DOI 2202
Semantics, Task analysis, Visualization, Interference, Stacking, Neural networks, Feature extraction, Focal attention, multimodal learning BibRef

Liu, B.Y.[Bing-Yuan], Malon, C.[Christopher], Xue, L.Z.[Ling-Zhou], Kruus, E.[Erik],
Improving Neural Network Robustness Through Neighborhood Preserving Layers,
IVC(123), 2022, pp. 104469.
Elsevier DOI 2206
BibRef
Earlier: ManifLearn20(179-195).
Springer DOI 2103
Deep learning, Manifold approximation, Neighborhood preservation, Robustness, Adversarial attack, Image classification BibRef

Jia, S.C.[Shao-Cheng], Yao, W.[Wei],
Joint learning of frequency and spatial domains for dense image prediction,
PandRS(195), 2023, pp. 14-28.
Elsevier DOI 2301

WWW Link. Apply to self-supervised depth estimation, ego-motion estimation, and semantic segmentation. Joint learning, Frequency learning, Spatial learning, Depth estimation, Semantic image segmentation BibRef

Yao, G.B.[Guo-Biao], Zhang, J.[Jin], Gong, J.Y.[Jian-Ya], Jin, F.X.[Feng-Xiang],
Automatic Production of Deep Learning Benchmark Dataset for Affine-Invariant Feature Matching,
IJGI(12), No. 2, 2023, pp. xx-yy.
DOI Link 2303
BibRef

Hang, R.L.[Ren-Long], Qian, X.[Xuwei], Liu, Q.S.[Qing-Shan],
MSNet: Multi-Resolution Synergistic Networks for Adaptive Inference,
CirSysVideo(33), No. 5, May 2023, pp. 2009-2018.
IEEE DOI
WWW Link. 2305
Adaptive systems, Image resolution, Feature extraction, Costs, Predictive models, Knowledge engineering, Adaptation models, image classification BibRef

Soflaei, M.[Masoumeh], Zhang, R.[Richong], Guo, H.Y.[Hong-Yu], Al-Bashabsheh, A.[Ali], Mao, Y.Y.[Yong-Yi],
Information Bottleneck and Aggregated Learning,
PAMI(45), No. 12, December 2023, pp. 14807-14820.
IEEE DOI 2311
BibRef

Zheng, Y.W.[Yao-Wei], Zhang, R.[Richong], Mao, Y.Y.[Yong-Yi],
Regularizing Neural Networks via Adversarial Model Perturbation,
CVPR21(8152-8161)
IEEE DOI 2111
Deep learning, Codes, Perturbation methods, Computational modeling, Neural networks, Tools BibRef


Lee, J.H.[Joon-Ho], Woo, J.O.[Jae Oh], Moon, H.K.[Han-Kyu], Lee, K.[Kwonho],
Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples,
ICCV23(16397-16406)
IEEE DOI 2401
BibRef

Müller, N.M.[Nicolas M.], Jacobs, J.[Jochen], Williams, J.[Jennifer], Böttinger, K.[Konstantin],
Localized Shortcut Removal,
XAI4CV23(3721-3725)
IEEE DOI 2309
BibRef

Chen, Y.H.[Yu-Hao], Zhang, S.[Shen], Song, R.J.[Ren-Jie],
Scoring Your Prediction on Unseen Data,
VDU23(3279-3288)
IEEE DOI 2309
BibRef

Pan, Z.Z.[Zi-Zheng], Cai, J.F.[Jian-Fei], Zhuang, B.[Bohan],
Stitchable Neural Networks,
CVPR23(16102-16112)
IEEE DOI 2309
BibRef

Liu, B.Y.[Bing-Yuan], Rony, J.[Jérôme], Galdran, A.[Adrian], Dolz, J.[Jose], Ayed, I.B.[Ismail Ben],
Class Adaptive Network Calibration,
CVPR23(16070-16079)
IEEE DOI 2309

WWW Link. BibRef

Shen, Y.[Yang], Sun, X.[Xuhao], Wei, X.S.[Xiu-Shen],
Equiangular Basis Vectors,
CVPR23(11755-11765)
IEEE DOI 2309

WWW Link. BibRef

Feng, R.[Ruili], Zheng, K.[Kecheng], Zhu, K.[Kai], Shen, Y.J.[Yu-Jun], Zhao, J.[Jian], Huang, Y.K.[Yu-Kun], Zhao, D.L.[De-Li], Zhou, J.R.[Jing-Ren], Jordan, M.[Michael], Zha, Z.J.[Zheng-Jun],
Neural Dependencies Emerging from Learning Massive Categories,
CVPR23(11711-11720)
IEEE DOI 2309

WWW Link. Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few other categories. BibRef

Cherian, A.[Anoop], Peng, K.C.[Kuan-Chuan], Lohit, S.[Suhas], Smith, K.A.[Kevin A.], Tenenbaum, J.B.[Joshua B.],
Are Deep Neural Networks SMARTer Than Second Graders?,
CVPR23(10834-10844)
IEEE DOI 2309
BibRef

Hänel, T.[Tobias], Kumar, N.[Nishant], Schlesinger, D.[Dmitrij], Li, M.Z.[Meng-Ze], Ünal, E.[Erdem], Eslami, A.[Abouzar], Gumhold, S.[Stefan],
Enhancing Fairness of Visual Attribute Predictors,
ACCV22(VI:151-167).
Springer DOI 2307
BibRef

Szabó, G.[Gergely], Horváth, A.[András],
Mitigating the Bias of Centered Objects in Common Datasets,
ICPR22(4786-4792)
IEEE DOI 2212
While CNNs are considered shift invariant, not always. Training, Image segmentation, Image edge detection, Boundary conditions, Task analysis BibRef

Tomani, C.[Christian], Cremers, D.[Daniel], Buettner, F.[Florian],
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration,
ECCV22(XIII:555-569).
Springer DOI 2211

WWW Link. BibRef

Pinto, F.[Francesco], Torr, P.H.S.[Philip H. S.], Dokania, P.K.[Puneet K.],
An Impartial Take to the CNN vs Transformer Robustness Contest,
ECCV22(XIII:466-480).
Springer DOI 2211
BibRef

Oh, J.H.[Jung-Hun], Kim, H.[Heewon], Baik, S.[Sungyong], Hong, C.[Cheeun], Lee, K.M.[Kyoung Mu],
Batch Normalization Tells You Which Filter is Important,
WACV22(3351-3360)
IEEE DOI 2202
Learning systems, Neural networks, Training data, Information filters, Data mining, Convolutional neural networks, Deep Learning -> Efficient Training and Inference Methods for Networks Object Detection/Recognition/Categorization BibRef

Laugros, A.[Alfred], Caplier, A.[Alice], Ospici, M.[Matthieu],
Using the Overlapping Score to Improve Corruption Benchmarks,
ICIP21(959-963)
IEEE DOI 2201
Study effect of blur, noise, lighting, etc. on NN analysis. Measurement, Image processing, Neural networks, Buildings, Benchmark testing, Robustness, Robustness, Benchmark, Corruptions BibRef

Shi, X.W.[Xiang-Wei], Li, Y.Q.[Yun-Qiang], Liu, X.[Xin], van Gemert, J.C.[Jan C.],
WeightAlign: Normalizing Activations by Weight Alignment,
ICPR21(9788-9795)
IEEE DOI 2105
Batch normalization in training. Training, Image segmentation, Semantics, Task analysis, Standards, Image classification BibRef

Horváth, A.[András], Al-Afandi, J.[Jalal],
Filtered Batch Normalization,
ICPR21(6778-6785)
IEEE DOI 2105
Training, Filtering, Neurons, Gaussian distribution, Kernel, Biological neural networks BibRef

Su, Y.C.[Ying-Cheng], Wu, Y.C.[Yi-Chao], Chen, K.[Ken], Liang, D.[Ding], Hu, X.L.[Xiao-Lin],
Dynamic Multi-path Neural Network,
ICPR21(4137-4144)
IEEE DOI 2105
Training, Performance evaluation, Runtime, Inference mechanisms, Neural networks, Network architecture, Logic gates BibRef

Forouzesh, M.[Mahsa], Salehi, F.[Farnood], Thiran, P.[Patrick],
Generalization Comparison of Deep Neural Networks via Output Sensitivity,
ICPR21(7411-7418)
IEEE DOI 2105
Training, Sensitivity, Neural networks, Labeling, deep neural networks, generalization, sensitivity, bias-variance decomposition BibRef

Rodríguez-Rodríguez, J.A.[José A.], Molina-Cabello, M.A.[Miguel A.], Benítez-Rochel, R.[Rafaela], López-Rubio, E.[Ezequiel],
The effect of image enhancement algorithms on convolutional neural networks,
ICPR21(3084-3089)
IEEE DOI 2105
Measurement, Brightness, Lighting, Classification algorithms, Convolutional neural networks, image enhancement techniques BibRef

Koçyigit, M.T.[Mustafa Taha], Sevilla-Lara, L.[Laura], Hospedales, T.M.[Timothy M.], Bilen, H.[Hakan],
Unsupervised Batch Normalization,
VL3W20(3994-3999)
IEEE DOI 2008
Improve convergence of NN training. Training, Standards, Manifolds, Task analysis, Architecture, Estimation, Optical imaging BibRef

Gómez-Flores, W.[Wilfrido], Sossa-Azuela, J.H.[Juan Humberto],
Towards Dendrite Spherical Neurons for Pattern Classification,
MCPR20(14-24).
Springer DOI 2007
BibRef

Tokmakov, P.[Pavel], Wang, Y.X.[Yu-Xiong], Hebert, M.[Martial],
Learning Compositional Representations for Few-Shot Recognition,
ICCV19(6371-6380)
IEEE DOI 2004
brain, image classification, image recognition, image representation, learning (artificial intelligence), Image coding BibRef

Zhuang, C.X.[Cheng-Xu], Zhai, A.[Alex], Yamins, D.[Daniel],
Local Aggregation for Unsupervised Learning of Visual Embeddings,
ICCV19(6001-6011)
IEEE DOI 2004
convolutional neural nets, learning (artificial intelligence), object detection, object recognition, pattern clustering, Unsupervised learning BibRef

Xie, S., Kirillov, A., Girshick, R., He, K.,
Exploring Randomly Wired Neural Networks for Image Recognition,
ICCV19(1284-1293)
IEEE DOI 2004
graph theory, image recognition, neural net architecture, optimisation, random processes, stochastic processes, Probability distribution BibRef

Tsotsos, J., Kotseruba, I., Andreopoulos, A., Wu, Y.,
Why Does Data-Driven Beat Theory-Driven Computer Vision?,
NeruArch19(2057-2060)
IEEE DOI 2004
learning (artificial intelligence), common vision datasets, theory-driven algorithms, theory driven vision BibRef

Lin, W.[Wang], Yang, Z.F.[Zheng-Feng], Chen, X.[Xin], Zhao, Q.Y.[Qing-Ye], Li, X.K.[Xiang-Kun], Liu, Z.M.[Zhi-Ming], He, J.F.[Ji-Feng],
Robustness Verification of Classification Deep Neural Networks via Linear Programming,
CVPR19(11410-11419).
IEEE DOI 2002
BibRef

Zhang, C.Q.[Chang-Qing], Liu, Y.Q.[Ye-Qing], Fu, H.Z.[Hua-Zhu],
AE2-Nets: Autoencoder in Autoencoder Networks,
CVPR19(2572-2580).
IEEE DOI 2002
BibRef

Zhang, L.H.[Li-Heng], Qi, G.J.[Guo-Jun], Wang, L.Q.[Li-Qiang], Luo, J.B.[Jie-Bo],
AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Data,
CVPR19(2542-2550).
IEEE DOI 2002
BibRef

Li, Y.[Yi], Kuang, Z.H.[Zhang-Hui], Chen, Y.M.[Yi-Min], Zhang, W.[Wayne],
Data-Driven Neuron Allocation for Scale Aggregation Networks,
CVPR19(11518-11526).
IEEE DOI 2002
BibRef

Wang, G.[Guangrun], Wang, K.[Keze], Lin, L.[Liang],
Adaptively Connected Neural Networks,
CVPR19(1781-1790).
IEEE DOI 2002
BibRef

Alcorn, M.A.[Michael A.], Li, Q.[Qi], Gong, Z.[Zhitao], Wang, C.F.[Cheng-Fei], Mai, L.[Long], Ku, W.S.[Wei-Shinn], Nguyen, A.[Anh],
Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects,
CVPR19(4840-4849).
IEEE DOI 2002
BibRef

Zhao, K., Matsukawa, T., Suzuki, E.,
Retraining: A Simple Way to Improve the Ensemble Accuracy of Deep Neural Networks for Image Classification,
ICPR18(860-867)
IEEE DOI 1812
Training, Biological system modeling, Task analysis, Optimization, Neural networks, Learning systems, Standards BibRef

Maier, A.[Andreas], Schebesch, F.[Frank], Syben, C.[Christopher], Würfl, T.[Tobias], Steidl, S.[Stefan], Choi, J.H.[Jang-Hwan], Fahrig, R.[Rebecca],
Precision Learning: Towards Use of Known Operators in Neural Networks,
ICPR18(183-188)
IEEE DOI 1812
Transforms, Neural networks, Needles, Upper bound, Training, Plastics, Pattern recognition BibRef

Wang, P.S.[Pei-Song], Hu, Q.H.[Qing-Hao], Zhang, Y.F.[Yi-Fan], Zhang, C.J.[Chun-Jie], Liu, Y.[Yang], Cheng, J.[Jian],
Two-Step Quantization for Low-Bit Neural Networks,
CVPR18(4376-4384)
IEEE DOI 1812
Quantization (signal), Hardware, Biological neural networks, Optimization, Training, Acceleration BibRef

Shen, H.,
Towards a Mathematical Understanding of the Difficulty in Learning with Feedforward Neural Networks,
CVPR18(811-820)
IEEE DOI 1812
Training, Approximation algorithms, Optimization, Convergence, Task analysis, Topology, Supervised learning BibRef

Murdock, C.[Calvin], Chang, M.F.[Ming-Fang], Lucey, S.[Simon],
Deep Component Analysis via Alternating Direction Neural Networks,
ECCV18(XV: 851-867).
Springer DOI 1810
BibRef

Velasco-Montero, D.[Delia], Fernández-Berni, J.[Jorge], Carmona-Galán, R.[Ricardo], Rodríguez-Vázquez, Á.[Ángel],
Optimum Network/Framework Selection from High-Level Specifications in Embedded Deep Learning Vision Applications,
ACIVS18(369-379).
Springer DOI 1810
Benchmarks 16 combinations of popular Deep Neural Networks for 1000-category image recognition. BibRef

Li, H.Y.[Hong-Yang], Guo, X.Y.[Xiao-Yang], Dai, B.[Bo], Ouyang, W.L.[Wan-Li], Wang, X.G.[Xiao-Gang],
Neural Network Encapsulation,
ECCV18(XI: 266-282).
Springer DOI 1810
BibRef

Cheng, H.[Hao], Lian, D.Z.[Dong-Ze], Gao, S.H.[Sheng-Hua], Geng, Y.L.[Yan-Lin],
Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane,
ECCV18(XI: 181-195).
Springer DOI 1810
BibRef

Liu, X.Q.[Xuan-Qing], Cheng, M.H.[Min-Hao], Zhang, H.[Huan], Hsieh, C.J.[Cho-Jui],
Towards Robust Neural Networks via Random Self-Ensemble,
ECCV18(VII: 381-397).
Springer DOI 1810
BibRef

Su, D.[Dong], Zhang, H.[Huan], Chen, H.G.[Hong-Ge], Yi, J.F.[Jin-Feng], Chen, P.Y.[Pin-Yu], Gao, Y.P.[Yu-Peng],
Is Robustness the Cost of Accuracy?: A Comprehensive Study on the Robustness of 18 Deep Image Classification Models,
ECCV18(XII: 644-661).
Springer DOI 1810
BibRef

Stock, P.[Pierre], Cisse, M.[Moustapha],
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases,
ECCV18(VI: 504-519).
Springer DOI 1810
BibRef

Wang, J., Russakovsky, O., Ramanan, D.,
The More You Look, the More You See: Towards General Object Understanding Through Recursive Refinement,
WACV18(1794-1803)
IEEE DOI 1806
feature extraction, image segmentation, inference mechanisms, learning (artificial intelligence), neural nets, Visualization BibRef

Goh, G.B., Siegel, C., Vishnu, A., Hodas, N., Baker, N.,
How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?,
WACV18(1340-1349)
IEEE DOI 1806
free energy, image representation, learning (artificial intelligence), neural nets, CNN models, Task analysis BibRef

Yuan, B., Chen, J., Zhang, W., Tai, H.S., McMains, S.,
Iterative Cross Learning on Noisy Labels,
WACV18(757-765)
IEEE DOI 1806
incorrect labels in training data. convolution, feedforward neural nets, image classification, iterative methods, Iterative Cross Learning, Training data BibRef

Novotny, D.[David], Larlus, D.[Diane], Vedaldi, A.[Andrea],
I Have Seen Enough: Transferring Parts Across Categories,
BMVC16(xx-yy).
HTML Version. 1805
Whether further progress can be indefinitely sustained by annotating more data, or whether there is a saturation point beyond which a problem is essentially solved, or the capacity of a model is saturated. A few thousand examples. BibRef

Stabinger, S., Rodríguez-Sánchez, A.,
Evaluation of Deep Learning on an Abstract Image Classification Dataset,
CogCV17(2767-2772)
IEEE DOI 1802
Cameras, Concrete, Machine learning, Training BibRef

Hou, S.H.[Sai-Hui], Liu, X.[Xu], Wang, Z.L.[Zi-Lei],
DualNet: Learn Complementary Features for Image Recognition,
ICCV17(502-510)
IEEE DOI 1802
2 parallel neural nets. feature extraction, image classification, image representation, learning (artificial intelligence), neural nets, Dual-Net, DualNet, Visualization BibRef

Eisenschtat, A.[Aviv], Wolf, L.B.[Lior B.],
Linking Image and Text with 2-Way Nets,
CVPR17(1855-1865)
IEEE DOI 1711
Adaptation models, Computer architecture, Correlation, Neurons, Training BibRef

Papandreou, G.[George], Kokkinos, I.[Iasonas], Savalle, P.A.[Pierre-Andre],
Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection,
CVPR15(390-399)
IEEE DOI 1510
BibRef

Zhou, X.Z.[Xiang-Zeng], Xie, L.[Lei], Zhang, P.[Peng], Zhang, Y.N.[Yan-Ning],
An ensemble of deep neural networks for object tracking,
ICIP14(843-847)
IEEE DOI 1502
Boosting BibRef

Miclut, B.[Bogdan],
Committees of Deep Feedforward Networks Trained with Few Data,
GCPR14(736-742).
Springer DOI 1411
BibRef

Yu, W.[Wei], Yang, K.Y.[Kui-Yuan], Bai, Y.L.[Ya-Long], Yao, H.X.[Hong-Xun], Rui, Y.[Yong],
DNN Flow: DNN Feature Pyramid based Image Matching,
BMVC14(xx-yy).
HTML Version. 1410
Deep Neural Network BibRef

Agrawal, P.[Pulkit], Girshick, R.[Ross], Malik, J.[Jitendra],
Analyzing the Performance of Multilayer Neural Networks for Object Recognition,
ECCV14(VII: 329-344).
Springer DOI 1408
BibRef

Chakraborty, D.[Debrup],
Neural Network Ensembles from Training Set Expansions,
CIARP09(629-636).
Springer DOI 0911
BibRef

Húsek, D.[Dušan], Moravec, P.[Pavel], Snášel, V.[Václav], Frolov, A.[Alexander], Rezanková, H.[Hana], Polyakov, P.[Pavel],
Comparison of Neural Network Boolean Factor Analysis Method with Some Other Dimension Reduction Methods on Bars Problem,
PReMI07(235-243).
Springer DOI 0712
BibRef

Sridharan, K.[Karthik], Beal, M.J.[Matthew J.], Govindaraju, V.[Venu],
Competitive Mixtures of Simple Neurons,
ICPR06(II: 494-497).
IEEE DOI 0609
BibRef

Lefebvre, G.[Gregoire], Laurent, C.[Christophe], Ros, J.[Julien], Garcia, C.[Christophe],
Supervised Image Classification by SOM Activity Map Comparison,
ICPR06(II: 728-731).
IEEE DOI 0609
BibRef

Ros, J.[Julien], Laurent, C.[Christophe], Lefebvre, G.[Grégoire],
A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification,
CIVR06(92-101).
Springer DOI 0607

See also Bag of Strings Representation for Image Categorization, A. BibRef

Qin, K.[Ke], Oommen, B.J.[B. John],
Chaotic Pattern Recognition: The Spectrum of Properties of the Adachi Neural Network,
SSPR08(540-550).
Springer DOI 0812
BibRef

Calitoiu, D.[Dragos], Oommen, J.B.[John B.], Nussbaum, D.[Doron],
Modeling Inaccurate Perception: Desynchronization Issues of a Chaotic Pattern Recognition Neural Network,
SCIA05(821-830).
Springer DOI 0506
BibRef

Adeodato, P.J.L., Vasconcelos, G.C., Arnaud, A.L., Cunha, R.C.L.V., Monteiro, D.S.M.P.,
A systematic solution for the NN3 Forecasting Competition problem based on an ensemble of MLP neural networks,
ICPR08(1-4).
IEEE DOI 0812
Multilayer Perceptron BibRef

Adeodato, P.J.L., Vasconcelos, G.C., Arnaud, A.L., Santos, R.A.F., Cunha, R.C.L.V., Monteiro, D.S.M.P.,
Neural Networks vs. Logistic Regression: A Comparative Study on a Large Data Set,
ICPR04(III: 355-358).
IEEE DOI 0409
BibRef

Steinkraus, D., Buck, I., Simard, P.Y.,
Using GPUs for machine learning algorithms,
ICDAR05(II: 1115-1120).
IEEE DOI 0508
BibRef

Doering, A., Witte, H.,
Feedforward Neural Networks for Bayes-Optimal Classification: Investigations on the Influence of the Composition of the Training Set on the Cost Function,
ICPR96(IV: 219-223).
IEEE DOI 9608
(Klinikum der Friedrich Schiller-Univ. D) BibRef

Holt, M.J.J.,
Comparison of generalization in multi-layer perceptrons with the log-likelihood and least-squares cost functions,
ICPR92(II:17-20).
IEEE DOI 9208
BibRef

Chen, C.H.,
A comparison of neural network models for pattern recognition,
ICPR90(II: 45-46).
IEEE DOI 9208
BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Neural Architecture, Network Structure .


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