14.5.2 Learning, General Surveys, Overviews

Open Deep Learning Toolkit for Robotics (OpenDR),
2021.
WWW Link.
WWW Link.
WWW Link. Code, Deep Learning.
WWW Link. 2201
Updated to version 3.0, with more features. The toolkit provides more than 20 methods, for human pose estimation, face detection, recognition, facial expression recognition, semantic and panoptic segmentation, video and skeleton-based action recognition, image, multimodal and point cloud-based object detection, 2D and 3D object tracking, speech command recognition, heart anomaly detection, navigation for wheeled robots, and grasping.

Schwartz, S.R., Wah, B.W.[Benjamin W.],
Machine Learning of Computer Vision Algorithms,
HPRIP-CV94(319-359). BibRef 9400

Fu, K.S., ed.,
Pattern Recognition and Machine Learning,
PlenumPress, New York, 1971. BibRef 7100

Bhanu, B., Poggio, T.,
Introduction to the Special Section on Learning in Computer Vision,
PAMI(16), No. 9, September 1994, pp. 865-867.
IEEE Top Reference. BibRef 9409

Bhanu, B., Peng, J., Huang, T., Draper, B.,
Introduction to the Special Issue on Learning in Computer Vision and Pattern Recognition,
SMC-B(35), No. 3, June 2005, pp. 391-396.
IEEE DOI 0508
BibRef

Vapnik, V.,
The Nature of Statistical Learning Theory,
Springer-Verlag1996. BibRef 9600

Vapnik, V.,
Statistical Learning Theory,
John Wiley& Sons, 1998. BibRef 9800

Vapnik, V.[Vladimir],
An overview of statistical learning theory,
TNN(10), No. 5, 1999, pp. 988-999. 0906
BibRef

Dietterich, T.G.,
Machine Learning Research: Four Current Directions,
AI Magazine(18), No. 4, 1997, pp. 97-136. BibRef 9700

Poggio, T.[Tomaso], Shelton, C.R.[Christian R.],
Machine Learning, Machine Vision, and the Brain,
AIMag(20), No. 3, Fall 1999, pp. 37-55. Regularization. Support Vector Machines. Survey, Learning. Survey of learning focused on a vision domain. Regularization, Support Vector Machines. Applied to face and pedestrian recognition. BibRef 9900

Petrou, M.[Maria],
Learning in Pattern Recognition: Some Thoughts,
PRL(22), No. 1, January 2001, pp. 3-13.
Elsevier DOI 0105
BibRef

Petrou, M.[Maria],
Learning in Computer Vision: Some Thoughts,
CIARP07(1-12).
Springer DOI 0711
BibRef

Xu, M.[Mai], Petrou, M.[Maria],
3D Scene interpretation by combining probability theory and logic: The tower of knowledge,
CVIU(115), No. 11, November 2011, pp. 1581-1596.
Elsevier DOI 1110
BibRef
Earlier:
Learning Logic Rules for Scene Interpretation Based on Markov Logic Networks,
ACCV09(III: 341-350).
Springer DOI 0909
BibRef
Earlier:
Recursive Tower of Knowledge for Learning to Interpret Scenes,
BMVC08(xx-yy).
PDF File. 0809
Scene labelling systems; Logic and probabilities; Machine learning; System architecture BibRef

Xu, M.[Mai], Wang, Z.[Zulin], Petrou, M.[Maria],
Tower of Knowledge for scene interpretation: A survey,
PRL(48), No. 1, 2014, pp. 42-48.
Elsevier DOI 1410
Tower of Knowledge. Cue of human language, for scene interpretation BibRef

Freeman, W.T.[William T.], Perona, P.[Pietro], Schölkopf, B.[Bernhard],
Guest Editorial Machine Learning for Vision,
IJCV(77), No. 1-3, May 2008, pp. 1.
Springer DOI 0803
BibRef

Raducanu, B.[Bogdan], Vitria, J.[Jordi],
Learning to learn: From smart machines to intelligent machines,
PRL(29), No. 8, 1 June 2008, pp. 1024-1032.
Elsevier DOI 0804
BibRef
Earlier:
Online Learning for Human-Robot Interaction,
Learning07(1-7).
IEEE DOI 0706
Incremental subspace learning based on Nonparametric Discriminant Analysis. Number of classes and samples not known and changes over time. Intelligent systems; Cognitive development; Context; Social robotics; Face recognition BibRef

Raducanu, B.[Bogdan], Vitria, J.[Jordi], Leonardis, A.[Ales],
Online pattern recognition and machine learning techniques for computer-vision: Theory and applications,
IVC(28), No. 7, July 2010, pp. 1063-1064.
Elsevier DOI 1006
Introduction to special issue. BibRef

Ioannidou, A.[Anastasia], Chatzilari, E.[Elisavet], Nikolopoulos, S.[Spiros], Kompatsiaris, I.[Ioannis],
Deep Learning Advances in Computer Vision with 3D Data: A Survey,
Surveys(50), No. 2, June 2017, pp. Article No 20.
DOI Link 1708
Survey, Deep Learning. This article surveys methods applying deep learning on 3D data and provides a classification based on how they exploit them. From the results of the examined works, we conclude that systems employing 2D views of 3D data typically surpass voxel-based (3D) deep models, which however, can perform better with more layers and severe data augmentation. Therefore, larger-scale datasets and increased resolutions are required. BibRef

McCann, M.T., Jin, K.H., Unser, M.,
Convolutional Neural Networks for Inverse Problems in Imaging: A Review,
SPMag(34), No. 6, November 2017, pp. 85-95.
IEEE DOI 1712
Survey, Convolutional Neural Networks. Computed tomography, Image reconstruction, Image resolution, Image segmentation, Inverse problems, Linear programming, Noise reduction BibRef

Jin, K.H., McCann, M.T., Froustey, E., Unser, M.,
Deep Convolutional Neural Network for Inverse Problems in Imaging,
IP(26), No. 9, September 2017, pp. 4509-4522.
IEEE DOI 1708
computerised tomography, feedforward neural nets, image resolution, iterative methods, learning (artificial intelligence), medical image processing, BibRef

Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.,
Deep Reinforcement Learning: A Brief Survey,
SPMag(34), No. 6, November 2017, pp. 26-38.
IEEE DOI 1712
Survey, Deep Learning. Artificial intelligence, Learning (artificial intelligence), Machine learning, Neural networks, Signal processing algorithms, Visualization BibRef

Fawzi, A.[Alhussein], Moosavi-Dezfooli, S.M.[Seyed-Mohsen], Frossard, P.[Pascal],
The Robustness of Deep Networks: A Geometrical Perspective,
SPMag(34), No. 6, November 2017, pp. 50-62.
IEEE DOI 1712
Classification, Machine learning, Neural networks, Robustness, Visualization BibRef

Darrell, T.J., Lampert, C.H., Sebe, N., Wu, Y., Yan, Y.,
Guest Editors' Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis,
PAMI(40), No. 5, May 2018, pp. 1029-1031.
IEEE DOI 1804
Collaboration, Information sharing, Learning systems, Machine learning, Multimedia communication, Training data BibRef

Nagy, G.[George],
Document analysis systems that improve with use,
IJDAR(23), No. 1, January 2020, pp. 13-29.
WWW Link. 2003
BibRef
Earlier:
Estimation, Learning, and Adaptation: Systems That Improve with Use,
SSSPR12(1-10).
Springer DOI 1211
BibRef
Earlier:
Persistent Issues in Learning and Estimation,
ICPR98(Vol I: 561-564).
IEEE DOI 9808
BibRef

Qin, H.T.[Hao-Tong], Gong, R.H.[Rui-Hao], Liu, X.L.[Xiang-Long], Bai, X.[Xiao], Song, J.K.[Jing-Kuan], Sebe, N.[Nicu],
Binary neural networks: A survey,
PR(105), 2020, pp. 107281.
Elsevier DOI 2006
Binary neural network, Deep learning, Model compression, Network quantization, Model acceleration BibRef

Serban, A.[Alex], Poll, E.[Erik], Visser, J.[Joost],
Adversarial Examples on Object Recognition: A Comprehensive Survey,
Surveys(53), No. 3, June 2020, pp. xx-yy.
DOI Link 2007
Survey, Adversairal Networks. security, robustness, machine learning, Adversarial examples BibRef

Goodfellow, I.[Ian], Pouget-Abadie, J.[Jean], Mirza, M.[Mehdi], Xu, B.[Bing], Warde-Farley, D.[David], Ozair, S.[Sherjil], Courville, A.[Aaron], Bengio, Y.[Yoshua],
Generative Adversarial Networks,
CACM(63), No. 11, November 2020, pp. 139-144.
DOI Link 2010
Survey, GAN. BibRef

Wang, Z.W.[Zheng-Wei], She, Q.[Qi], Ward, T.E.[Tomas E.],
Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy,
Surveys(54), No. 2, February 2021, pp. xx-yy.
DOI Link 2104
Survey, GAN. Generative adversarial networks, loss-variants, stabilizing training, architecture-variants BibRef

Das, R.[Rangan], Sen, S.[Sagnik], Maulik, U.[Ujjwal],
A Survey on Fuzzy Deep Neural Networks,
Surveys(53), No. 3, May 2020, pp. xx-yy.
DOI Link 2007
Survey, Deep Networks. parallel models, integrated models, sequential models, ensemble models, fuzzy systems, Deep architecture BibRef

Wang, H.[Hao], Yeung, D.Y.[Dit-Yan],
A Survey on Bayesian Deep Learning,
Surveys(53), No. 5, September 2020, pp. xx-yy.
DOI Link 2010
generative models, Deep learning, Bayesian networks, probabilistic graphical models BibRef

Samek, W., Montavon, G., Lapuschkin, S., Anders, C.J., Müller, K.R.,
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications,
PIEEE(109), No. 3, March 2021, pp. 247-278.
IEEE DOI 2103
Survey, Deep Learning. Deep learning, Systematics, Neural networks, Artificial intelligence, Machine learning, Unsupervised learning, neural networks BibRef

Saxena, D.[Divya], Cao, J.N.[Jian-Nong],
Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions,
Surveys(54), No. 3, May 2021, pp. xx-yy.
DOI Link 2106
Survey, GAN. GANs variants, GANs Survey, Image generation, GANs challenges, GANs, mode collapse, deep Generative models BibRef

Jabbar, A.[Abdul], Li, X.[Xi], Omar, B.[Bourahla],
A Survey on Generative Adversarial Networks: Variants, Applications, and Training,
Surveys(54), No. 8, October 2021, pp. xx-yy.
DOI Link 2110
Survey, GAN. architectural-variants, stabilize training, Generative Adversarial Networks (GANs), applications BibRef

Chen, L.Y.[Lei-Yu], Li, S.B.[Shao-Bo], Bai, Q.[Qiang], Yang, J.[Jing], Jiang, S.L.[San-Long], Miao, Y.M.[Yan-Ming],
Review of Image Classification Algorithms Based on Convolutional Neural Networks,
RS(13), No. 22, 2021, pp. xx-yy.
DOI Link 2112
Survey, CNN. BibRef

Borji, A.[Ali],
Pros and cons of GAN evaluation measures: New developments,
CVIU(215), 2022, pp. 103329.
Elsevier DOI 2201
GAN evaluation, Generative modeling, Deepfakes BibRef

Soviany, P.[Petru], Ionescu, R.T.[Radu Tudor], Rota, P.[Paolo], Sebe, N.[Nicu],
Curriculum Learning: A Survey,
IJCV(130), No. 6, June 2022, pp. 1526-1565.
Springer DOI 2207
Survey, Curriculum Learning. BibRef

Sánchez-Cauce, R.[Raquel], París, I.[Iago], Díez, F.J.[Francisco Javier],
Sum-Product Networks: A Survey,
PAMI(44), No. 7, July 2022, pp. 3821-3839.
IEEE DOI 2206
Probabilistic logic, Artificial neural networks, Probability distribution, Neural networks, Bayes methods, deep neural networks BibRef

Mandal, M.[Murari], Vipparthi, S.K.[Santosh Kumar],
An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs,
ITS(23), No. 7, July 2022, pp. 6101-6122.
IEEE DOI 2207
Deep learning, Training, Task analysis, Data models, Computational modeling, Cameras, Benchmark testing, scene independence BibRef

Wang, X.[Xin], Chen, Y.D.[Yu-Dong], Zhu, W.W.[Wen-Wu],
A Survey on Curriculum Learning,
PAMI(44), No. 9, September 2022, pp. 4555-4576.
IEEE DOI 2208
Training, Task analysis, Machine learning, Data models, Convergence, Machine learning algorithms, Computational modeling, self-paced learning BibRef

Hospedales, T.M.[Timothy M.], Antoniou, A.[Antreas], Micaelli, P.[Paul], Storkey, A.[Amos],
Meta-Learning in Neural Networks: A Survey,
PAMI(44), No. 9, September 2022, pp. 5149-5169.
IEEE DOI 2208
Task analysis, Optimization, Training, Machine learning algorithms, Predictive models, Neural networks, Deep learning, Meta-learning, neural architecture search BibRef

Bond-Taylor, S.[Sam], Leach, A.[Adam], Long, Y.[Yang], Willcocks, C.G.[Chris G.],
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models,
PAMI(44), No. 11, November 2022, pp. 7327-7347.
IEEE DOI 2210
Survey, Generative Modeling. Data models, Training, Computational modeling, Analytical models, Generative adversarial networks, Predictive models, Neurons, normalizing flows BibRef

Liu, R.S.[Ri-Sheng], Gao, J.X.[Jia-Xin], Zhang, J.[Jin], Meng, D.Y.[De-Yu], Lin, Z.C.[Zhou-Chen],
Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond,
PAMI(44), No. 12, December 2022, pp. 10045-10067.
IEEE DOI 2212
Optimization, Task analysis, Convergence, Complexity theory, Reinforcement learning, Multitasking, Bi-level optimization, Explicit and implicit gradients BibRef

Li, Z.Q.[Zi-Qiang], Usman, M.[Muhammad], Tao, R.[Rentuo], Xia, P.F.[Peng-Fei], Wang, C.[Chaoyue], Chen, H.[Huanhuan], Li, B.[Bin],
A Systematic Survey of Regularization and Normalization in GANs,
Surveys(55), No. 11, February 2023, pp. xx-yy.
DOI Link 2303
Training Dynamics, Generative Adversarial Networks, Lipschitz Neural networks BibRef

Qayyum, A.[Adnan], Ilahi, I.[Inaam], Shamshad, F.[Fahad], Boussaid, F.[Farid], Bennamoun, M.[Mohammed], Qadir, J.[Junaid],
Untrained Neural Network Priors for Inverse Imaging Problems: A Survey,
PAMI(45), No. 5, May 2023, pp. 6511-6536.
IEEE DOI 2304
Inverse problems, Neural networks, Imaging, Task analysis, Image reconstruction, Noise measurement, Deep learning, deep learning BibRef

Peng, S.Y.[Si-Yuan], Lu, J.[Jing], Cao, J.Z.[Jiang-Zhong], Peng, Q.M.[Qiao-Mei], Yang, Z.J.[Zhi-Jing],
Adaptive graph regularization method based on least square regression for clustering,
SP:IC(114), 2023, pp. 116938.
Elsevier DOI 2305
Adaptive graph regularization, Least squares regression, Low-rank representation, Frobenius norm, Clustering BibRef

Stankovic, L.[Ljubiša], Mandic, D.[Danilo],
Convolutional Neural Networks Demystified: A Matched Filtering Perspective-Based Tutorial,
SMCS(53), No. 6, June 2023, pp. 3614-3628.
IEEE DOI 2305
Convolution, Noise measurement, Pattern matching, Feature extraction, Standards, Signal resolution, Filtering, matched filter BibRef

Huang, Y.[Yangsibo], Huang, C.Y.[Chun-Yin], Li, X.X.[Xiao-Xiao], Li, K.[Kai],
A Dataset Auditing Method for Collaboratively Trained Machine Learning Models,
MedImg(42), No. 7, July 2023, pp. 2081-2090.
IEEE DOI 2307
Data models, Training, Regulation, Calibration, Analytical models, Measurement, Robustness, Privacy, dataset auditing, medical image classification BibRef

Obukhov, T.[Timur], Brovelli, M.A.[Maria A.],
Identifying Conditioning Factors and Predictors of Conflict Likelihood for Machine Learning Models: A Literature Review,
IJGI(12), No. 8, 2023, pp. 322.
DOI Link 2309
BibRef

Bakhtiarnia, A.[Arian], Zhang, Q.[Qi], Iosifidis, A.[Alexandros],
Efficient High-Resolution Deep Learning: A Survey,
Surveys(56), No. 7, April 2024, pp. xx-yy.
DOI Link 2405
Survey, Deep Learning. High-resolution deep learning, efficient deep learning, vision transformer BibRef

Akar, C.A.[Chafic Abou], Massih, R.A.[Rachelle Abdel], Yaghi, A.[Anthony], Khalil, J.[Joe], Kamradt, M.[Marc], Makhoul, A.[Abdallah],
Generative Adversarial Network Applications in Industry 4.0: A Review,
IJCV(132), No. 6, June 2024, pp. 2195-2254.
Springer DOI 2406
BibRef

Mettes, P.[Pascal], Atigh, M.G.[Mina Ghadimi], Keller-Ressel, M.[Martin], Gu, J.[Jeffrey], Yeung, S.[Serena],
Hyperbolic Deep Learning in Computer Vision: A Survey,
IJCV(132), No. 1, January 2024, pp. 3484-3508.
Springer DOI 2409
Deep Learning. BibRef

Warner, E.[Elisa], Lee, J.[Joonsang], Hsu, W.[William], Syeda-Mahmood, T.[Tanveer], Kahn Jr., C.E.[Charles E.], Gevaert, O.[Olivier], Rao, A.[Arvind],
Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects,
IJCV(132), No. 1, January 2024, pp. 3753-3769.
Springer DOI 2409
BibRef

Ganesh, P.[Prakhar],
An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification,
WACV24(4476-4485)
IEEE DOI 2404
Measurement, Deep learning, Computational modeling, Benchmark testing, Market research, Image classification, Social good BibRef

Pathak, A.[Abha], Arya, K.V.[Karm Veer], Tiwari, V.[Vivek], Bhende, M.[Manisha],
Unveiling Image Classifiers: An In-Depth Comparative Exploration of Machine Learning Algorithms,
ICCVMI23(1-5)
IEEE DOI 2403
Support vector machines, Machine learning algorithms, Navigation, Heuristic algorithms, Classification algorithms, Content Moderation BibRef

Wang, Q.Y.[Qing-Yang], Powell, M.A.[Michael A.], Geisa, A.[Ali], Bridgeford, E.[Eric], Priebe, C.E.[Carey E.], Vogelstein, J.T.[Joshua T.],
Why do networks have inhibitory/negative connections?,
ICCV23(22494-22502)
IEEE DOI 2401
BibRef

Hanspal, H.[Harleen], Lomuscio, A.[Alessio],
Efficient Verification of Neural Networks Against LVM-Based Specifications,
CVPR23(3894-3903)
IEEE DOI 2309
BibRef

Matzinger, H.[Heinrich], Allgeier, A.[Allegra],
CNN Image Recognition is Mainly Based on Local Features,
ICRVC22(90-95)
IEEE DOI 2301
Image recognition, Shape, Robot sensing systems, Pattern recognition, Convolutional neural networks, artificial intelligence BibRef

Alfarra, M.[Motasem], Pérez, J.C.[Juan C.], Frühstück, A.[Anna], Torr, P.H.S.[Philip H. S.], Wonka, P.[Peter], Ghanem, B.[Bernard],
On the Robustness of Quality Measures for GANs,
ECCV22(XVII:18-33).
Springer DOI 2211
BibRef

Gavrikov, P.[Paul], Keuper, J.[Janis],
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters,
CVPR22(19044-19054)
IEEE DOI 2210

WWW Link. Convolution, Computational modeling, Information filters, Robustness, Entropy, Datasets and evaluation, Transfer/low-shot/long-tail learning BibRef

Gavrikov, P.[Paul], Keuper, J.[Janis],
Adversarial Robustness through the Lens of Convolutional Filters,
ArtOfRobust22(138-146)
IEEE DOI 2210
Training, Convolution, Perturbation methods, Predictive models, Robustness, Data models BibRef

Inkawhich, M.[Matthew], Inkawhich, N.[Nathan], Davis, E.[Eric], Li, H.[Hai], Chen, Y.[Yiran],
The Untapped Potential of Off-the-Shelf Convolutional Neural Networks,
WACV22(2907-2916)
IEEE DOI 2202
Training, Upper bound, Convolution, Network architecture, Inference algorithms, Data models, Vision Systems and Applications BibRef

Minskiy, D.[Dmitry], Bober, M.[Miroslaw],
Efficient Hybrid Network: Inducting Scattering Features,
ICPR22(2300-2306)
IEEE DOI 2212
BibRef
And:
Scattering-Based Hybrid Networks: An Evaluation and Design Guide,
ICIP21(2793-2797)
IEEE DOI 2201
Training, Force, Scattering, Training data, Performance gain, Stability analysis. Image resolution, System performance, Buildings, hybrid, network design BibRef

Zhou, H.Y.[Hong-Yu], Lu, C.X.[Chi-Xiang], Yang, S.[Sibei], Yu, Y.Z.[Yi-Zhou],
ConvNets vs. Transformers: Whose Visual Representations are More Transferable?,
DeepMTL21(2230-2238)
IEEE DOI 2112
Performance evaluation, Visualization, Face recognition, Transfer learning, Estimation BibRef

Wang, X.H.[Xiao-Han], Eliott, F.M.[Fernanda M.], Ainooson, J.[James], Palmer, J.H.[Joshua H.], Kunda, M.[Maithilee],
An Object is Worth Six Thousand Pictures: The Egocentric, Manual, Multi-image (EMMI) Dataset,
Egocentric17(2364-2372)
IEEE DOI
WWW Link. 1802
Dataset, Learning. Egocentric, Manual, Multi-Image (EMMI) Dataset. Automobiles, Cameras, Manuals, Object recognition, Toy manufacturing industry, Training, Visualization BibRef

Bala, J.W., Michalski, R.S., Wnek, J.,
The Prax Approach to Learning a Large Number of Texture Concepts,
AAAI-MLCV93(xx-yy). George Mason University. BibRef 9300

Bala, J.W., Michalski, R.S., and Pachowicz, P.W.,
Progress on Vision through Learning at George Mason University,
ARPA94(I:191-207). BibRef 9400

Michalski, R.S., Rosenfeld, A., Aloimonos, Y., Duric, Z., Maloof, M.A., Zhang, Q.,
Progress on Vision Through Learning,
ARPA96(177-188). BibRef 9600

Bhanu, B.[Bir], Bowyer, K.W.[Kevin W.], Hall, L.O.[Lawrence O.], and Langley, P.[Pat],
Report of the AAAI Fall Symposium on Machine Learning and Computer Vision: What, Why and How?,
ARPA94(I:727-731). BibRef 9400

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