14.5.10.7.17 Loss Functions, Triplet Loss Function, Deep Learning, Neural Netowrks

Chapter Contents (Back)
Deep Nets. Neural Networks. Loss Functions.
See also Deep Learning, Deep Nets.
See also Edge Detectors Based on Learning, Neural Nets, etc..

Singh, A.[Abhishek], Pokharel, R.[Rosha], Principe, J.C.[Jose C.],
The C-loss function for pattern classification,
PR(47), No. 1, 2014, pp. 441-453.
Elsevier DOI 1310
Correntropy. For neural network classification. BibRef

Liao, Z.B.[Zhi-Bin], Carneiro, G.[Gustavo],
A deep convolutional neural network module that promotes competition of multiple-size filters,
PR(71), No. 1, 2017, pp. 94-105.
Elsevier DOI 1707
BibRef
Earlier:
The use of deep learning features in a hierarchical classifier learned with the minimization of a non-greedy loss function that delays gratification,
ICIP15(4540-4544)
IEEE DOI 1512
Deep, learning BibRef

Agarwal, N.[Nakul], Balasubramanian, V.N.[Vineeth N.], Jawahar, C.V.,
Improving multiclass classification by deep networks using DAGSVM and Triplet Loss,
PRL(112), 2018, pp. 184-190.
Elsevier DOI 1809
Multiclass classification, Deep networks, DAGSVM, Triplet loss BibRef

Bazi, Y.[Yakoub], Rahhal, M.M.A.[Mohamad M. Al], Alhichri, H.[Haikel], Alajlan, N.[Naif],
Simple Yet Effective Fine-Tuning of Deep CNNs Using an Auxiliary Classification Loss for Remote Sensing Scene Classification,
RS(11), No. 24, 2019, pp. xx-yy.
DOI Link 1912
BibRef

Ren, C.X.[Chuan-Xian], Li, J.Z.[Ju-Zheng], Ge, P.F.[Peng-Fei], Xu, X.L.[Xiao-Lin],
Deep metric learning via subtype fuzzy clustering,
PR(90), 2019, pp. 210-219.
Elsevier DOI 1903
Metric learning, Deep networks, Triplet loss, Fuzzy clustering, Online sampling BibRef

Yuan, Q.Y.[Qun-Yong], Xiao, N.F.[Nan-Feng],
Experimental exploration on loss surface of deep neural network,
IJIST(30), No. 4, 2020, pp. 860-873.
DOI Link 2011
The loss function of the deep neural network is high dimensional, nonconvex and complex. loss surface of deep neural network, Hessian matrix deep neural network, ensemble learning BibRef

Yan, Y., Hao, H., Xu, B., Zhao, J., Shen, F.,
Image Clustering via Deep Embedded Dimensionality Reduction and Probability-Based Triplet Loss,
IP(29), 2020, pp. 5652-5661.
IEEE DOI 2005
Dimensionality reduction, Feature extraction, Loss measurement, Clustering algorithms, Unsupervised learning, Manifolds, dimensionality reduction BibRef

Li, C.J.[Cui-Jin], Qu, Z.[Zhong], Wang, S.Y.[Sheng-Ye], Liu, L.[Ling],
A method of cross-layer fusion multi-object detection and recognition based on improved faster R-CNN model in complex traffic environment,
PRL(145), 2021, pp. 127-134.
Elsevier DOI 2104
Multi-object detection, Multi-object recognition, Faster R-CNN, Weighted balanced multi-class cross entropy loss function BibRef

Seo, H., Bassenne, M., Xing, L.,
Closing the Gap Between Deep Neural Network Modeling and Biomedical Decision-Making Metrics in Segmentation via Adaptive Loss Functions,
MedImg(40), No. 2, February 2021, pp. 585-593.
IEEE DOI 2102
Training, Neural networks, Measurement, Adaptation models, Decision making, Deep learning, Harmonic analysis, Deep learning, Segmentation BibRef

Martínez-Cortés, T.[Tomás], González-Díaz, I.[Iván], Díaz-de-María, F.[Fernando],
Training deep retrieval models with noisy datasets: Bag exponential loss,
PR(112), 2021, pp. 107811.
Elsevier DOI 2102
Image retrieval, Noise, Multiple instance learning, Loss functions BibRef

Zadeh, S.G.[Shekoufeh Gorgi], Schmid, M.[Matthias],
Bias in Cross-Entropy-Based Training of Deep Survival Networks,
PAMI(43), No. 9, September 2021, pp. 3126-3137.
IEEE DOI 2108
Training, Hazards, Mathematical model, Entropy, Power measurement, Indexes, Neural networks, Cross-entropy loss, negative log-likelihood loss BibRef

Kang, J.[Jian], Fernandez-Beltran, R.[Ruben], Duan, P.[Puhong], Kang, X.D.[Xu-Dong], Plaza, A.J.[Antonio J.],
Robust Normalized Softmax Loss for Deep Metric Learning-Based Characterization of Remote Sensing Images With Label Noise,
GeoRS(59), No. 10, October 2021, pp. 8798-8811.
IEEE DOI 2109
Measurement, Semantics, Annotations, Feature extraction, Prototypes, Noise measurement, Visualization, Deep metric learning, remote sensing (RS) BibRef

Tian, Y.[Ye], Dong, Y.X.[Yu-Xin], Yin, G.S.[Gui-Sheng],
Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification,
RS(13), No. 20, 2021, pp. xx-yy.
DOI Link 2110
BibRef

Deng, W., Zheng, L., Sun, Y., Jiao, J.,
Rethinking Triplet Loss for Domain Adaptation,
CirSysVideo(31), No. 1, January 2021, pp. 29-37.
IEEE DOI 2101
Semantics, Feature extraction, Measurement, Adaptation models, Data models, Image color analysis, Sun, Domain adaptation, semantic alignment BibRef

Lyu, S.W.[Si-Wei], Fan, Y.B.[Yan-Bo], Ying, Y.M.[Yi-Ming], Hu, B.G.[Bao-Gang],
Average Top-k Aggregate Loss for Supervised Learning,
PAMI(44), No. 1, January 2022, pp. 76-86.
IEEE DOI 2112
Aggregates, Training, Training data, Supervised learning, Data models, Loss measurement, Task analysis, Aggregate loss, learning theory BibRef

Huang, K.K.[Ke-Kun], Ren, C.X.[Chuan-Xian], Liu, H.[Hui], Lai, Z.R.[Zhao-Rong], Yu, Y.F.[Yu-Feng], Dai, D.Q.[Dao-Qing],
Hyperspectral image classification via discriminative convolutional neural network with an improved triplet loss,
PR(112), 2021, pp. 107744.
Elsevier DOI 2102
Hyper-spectral image classification, Convolutional neural network, Triplet loss, Metric learning BibRef

Cao, Y.Z.[Yu-Zhou], Liu, S.Q.[Shu-Qi], Xu, Y.T.[Yi-Tian],
Multi-complementary and unlabeled learning for arbitrary losses and models,
PR(124), 2022, pp. 108447.
Elsevier DOI 2203
Multi-complementary, Unlabeled learning, Empirical risk minimization, Unbiased estimator, Classification BibRef

Zhang, Z.X.[Zhao-Xiang], Luo, C.C.[Chuan-Chen], Wu, H.P.[Hai-Ping], Chen, Y.T.[Yun-Tao], Wang, N.Y.[Nai-Yan], Song, C.F.[Chun-Feng],
From Individual to Whole: Reducing Intra-class Variance by Feature Aggregation,
IJCV(130), No. 3, March 2022, pp. 800-819.
Springer DOI 2203
Learn model. different viewpoints can be different model. BibRef

Murasaki, K.[Kazuhiko], Ando, S.[Shingo], Shimamura, J.[Jun],
Semi-Supervised Representation Learning via Triplet Loss Based on Explicit Class Ratio of Unlabeled Data,
IEICE(E105-D), No. 4, April 2022, pp. 778-784.
WWW Link. 2204
BibRef

Yan, C.[Cheng], Pang, G.[Guansong], Bai, X.[Xiao], Liu, C.H.[Chang-Hong], Ning, X.[Xin], Gu, L.[Lin], Zhou, J.[Jun],
Beyond Triplet Loss: Person Re-Identification With Fine-Grained Difference-Aware Pairwise Loss,
MultMed(24), 2022, pp. 1665-1677.
IEEE DOI 2204
Benchmark testing, Training, Feature extraction, Task analysis, Semantics, Pose estimation, Fine-grained difference, pairwise loss, triplet loss BibRef

Wu, S.K.[Sheng-Kai], Yang, J.R.[Jin-Rong], Wang, X.G.[Xing-Gang], Li, X.P.[Xiao-Ping],
IoU-Balanced loss functions for single-stage object detection,
PRL(156), 2022, pp. 96-103.
Elsevier DOI 2205
IoU-Balanced classification loss, IoU-Balanced localization loss, Object detection, Example mining BibRef

Mehta, D.[Dhagash], Chen, T.[Tianran], Tang, T.T.[Ting-Ting], Hauenstein, J.D.[Jonathan D.],
The Loss Surface of Deep Linear Networks Viewed Through the Algebraic Geometry Lens,
PAMI(44), No. 9, September 2022, pp. 5664-5680.
IEEE DOI 2208
Geometry, Mathematical model, Deep learning, Analytical models, Upper bound, Neurons, Task analysis, Deep linear network, numerical algebraic geometry BibRef

Zhang, Q.[Qiang], Yang, J.[Jibin], Zhang, X.[Xiongwei], Cao, T.Y.[Tie-Yong],
SO-softmax loss for discriminable embedding learning in CNNs,
PR(131), 2022, pp. 108877.
Elsevier DOI 2208
Convolutional neural networks, Cosine similarity, Cross entropy loss, Quadratic transformation, Softmax BibRef

Oner, D.[Doruk], Kozinski, M.[Mateusz], Citraro, L.[Leonardo], Dadap, N.C.[Nathan C.], Konings, A.G.[Alexandra G.], Fua, P.[Pascal],
Promoting Connectivity of Network-Like Structures by Enforcing Region Separation,
PAMI(44), No. 9, September 2022, pp. 5401-5413.
IEEE DOI 2208
Deep networks on network-like structures. Roads, Irrigation, Training, Image reconstruction, Image segmentation, Annotations, Topology, connectivity BibRef

Yao, Q.M.[Quan-Ming], Yang, H.[Hansi], Hu, E.L.[En-Liang], Kwok, J.T.[James T.],
Efficient Low-Rank Semidefinite Programming With Robust Loss Functions,
PAMI(44), No. 10, October 2022, pp. 6153-6168.
IEEE DOI 2209
Optimization, Convex functions, Convergence, Robustness, Machine learning algorithms, Sparse matrices, Symmetric matrices, alternating direction method of multipliers BibRef

Marchetti, F., Guastavino, S., Piana, M., Campi, C.,
Score-Oriented Loss (SOL) functions,
PR(132), 2022, pp. 108913.
Elsevier DOI 2209
Supervised machine learning, Binary classification, Loss functions, Skill scores BibRef

Clough, J.R.[James R.], Byrne, N.[Nicholas], Oksuz, I.[Ilkay], Zimmer, V.A.[Veronika A.], Schnabel, J.A.[Julia A.], King, A.P.[Andrew P.],
A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology,
PAMI(44), No. 12, December 2022, pp. 8766-8778.
IEEE DOI 2212
Image segmentation, Topology, Shape, Training, Loss measurement, Neural networks, Network topology, Segmentation, convolutional neural networks BibRef

Charte, D.[David], Charte, F.[Francisco], Herrera, F.[Francisco],
Reducing Data Complexity Using Autoencoders With Class-Informed Loss Functions,
PAMI(44), No. 12, December 2022, pp. 9549-9560.
IEEE DOI 2212
Complexity theory, Feature extraction, Measurement, Shape, Support vector machines, Data models, Transforms, Autoencoders, data complexity BibRef

Wu, H.X.[Han-Xiao], Shen, F.[Fei], Zhu, J.Q.[Jian-Qing], Zeng, H.Q.[Huan-Qiang], Zhu, X.B.[Xia-Bin], Lei, Z.[Zhen],
A sample-proxy dual triplet loss function for object re-identification,
IET-IPR(16), No. 14, 2022, pp. 3781-3789.
DOI Link 2212
BibRef


Croitoru, F.A.[Florinel-Alin], Grigore, D.N.[Diana-Nicoleta], Ionescu, R.T.[Radu Tudor],
Discriminability-enforcing loss to improve representation learning,
ECV22(2597-2601)
IEEE DOI 2210
Training, Representation learning, Impurities, Neural networks, Transformers, Entropy BibRef

Patel, Y.[Yash], Tolias, G.[Giorgos], Matas, J.[Jirí],
Recall@k Surrogate Loss with Large Batches and Similarity Mixup,
CVPR22(7492-7501)
IEEE DOI 2210
Measurement, Training, Visualization, Memory management, Image retrieval, Graphics processing units, Benchmark testing, Representation learning BibRef

Li, H.[Hao], Fu, T.[Tianwen], Dai, J.[Jifeng], Li, H.S.[Hong-Sheng], Huang, G.[Gao], Zhu, X.[Xizhou],
AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks,
CVPR22(999-1008)
IEEE DOI 2210
Protocols, Codes, Evolutionary computation, Extraterrestrial measurements, Pattern recognition, Scene analysis and understanding BibRef

Hebbalaguppe, R.[Ramya], Prakash, J.[Jatin], Madan, N.[Neelabh], Arora, C.[Chetan],
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration,
CVPR22(16060-16069)
IEEE DOI 2210
Training, Image segmentation, Neural networks, Semantics, Natural languages, Picture archiving and communication systems, privacy and ethics in vision BibRef

Han, D.[Dasol], Yoo, J.W.[Jae-Wook], Oh, D.[Dokwan],
SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information,
CVPR22(4453-4462)
IEEE DOI 2210
Deep learning, Shape, Semantics, Transfer learning, Neural networks, Object detection, Benchmark testing, Segmentation, Scene analysis and understanding BibRef

Lim, J.[Jongin], Yun, S.[Sangdoo], Park, S.[Seulki], Choi, J.Y.[Jin Young],
Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning,
CVPR22(212-222)
IEEE DOI 2210
Measurement, Representation learning, Visualization, Computational modeling, Semantics, Neural networks, Transfer/low-shot/long-tail learning BibRef

Abrahamyan, L.[Lusine], Ziatchin, V.[Valentin], Chen, Y.M.[Yi-Ming], Deligiannis, N.[Nikos],
Bias Loss for Mobile Neural Networks,
ICCV21(6536-6546)
IEEE DOI 2203
Training, Computational modeling, Neural networks, Benchmark testing, Data models, Scene analysis and understanding BibRef

Scott, T.R.[Tyler R.], Gallagher, A.C.[Andrew C.], Mozer, M.C.[Michael C.],
von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning,
ICCV21(10592-10602)
IEEE DOI 2203
Geometry, Training, Systematics, Transfer learning, Supervised learning, Stochastic processes, Predictive models, Recognition and classification BibRef

Warburg, F.[Frederik], Jřrgensen, M.[Martin], Civera, J.[Javier], Hauberg, S.[Sřren],
Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval,
ICCV21(12138-12148)
IEEE DOI 2203
Uncertainty, Computational modeling, Image retrieval, Stochastic processes, Bayes methods, Computational efficiency, BibRef

Ranasinghe, K.[Kanchana], Naseer, M.[Muzammal], Hayat, M.[Munawar], Khan, S.[Salman], Khan, F.S.[Fahad Shahbaz],
Orthogonal Projection Loss,
ICCV21(12313-12323)
IEEE DOI 2203
Deep learning, Image recognition, Neural networks, Force, Linear programming, Robustness, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Samuel, D.[Dvir], Chechik, G.[Gal],
Distributional Robustness Loss for Long-tail Learning,
ICCV21(9475-9484)
IEEE DOI 2203
Training, Head, Upper bound, Computational modeling, Benchmark testing, Feature extraction, Representation learning BibRef

Mullapudi, R.T.[Ravi Teja], Poms, F.[Fait], Mark, W.R.[William R.], Ramanan, D.[Deva], Fatahalian, K.[Kayvon],
Learning Rare Category Classifiers on a Tight Labeling Budget,
ICCV21(8403-8412)
IEEE DOI 2203
Training, Representation learning, Adaptation models, Buildings, Propagation losses, Data models, Labeling, Efficient training and inference methods BibRef

Yu, N.[Ning], Liu, G.[Guilin], Dundar, A.[Aysegul], Tao, A.[Andrew], Catanzaro, B.[Bryan], Davis, L.[Larry], Fritz, M.[Mario],
Dual Contrastive Loss and Attention for GANs,
ICCV21(6711-6722)
IEEE DOI 2203
Image synthesis, Benchmark testing, Generative adversarial networks, Generators, Image and video synthesis BibRef

Yuan, Z.N.[Zhuo-Ning], Yan, Y.[Yan], Sonka, M.[Milan], Yang, T.B.[Tian-Bao],
Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification,
ICCV21(3020-3029)
IEEE DOI 2203

WWW Link. Dams, Stochastic processes, Benchmark testing, Skin, Task analysis, Optimization, X-ray imaging, Optimization and learning methods, Recognition and classification BibRef

Wang, C.F.[Chao-Fei], Xiao, J.[Jiayu], Han, Y.Z.[Yi-Zeng], Yang, Q.[Qisen], Song, S.[Shiji], Huang, G.[Gao],
Towards Learning Spatially Discriminative Feature Representations,
ICCV21(1306-1315)
IEEE DOI 2203
CAM-loss, to constrain the embedded feature maps with the class activation maps. Visualization, Transfer learning, Drives, Feature extraction, Cams, Recognition and classification, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Ridnik, T.[Tal], Ben-Baruch, E.[Emanuel], Zamir, N.[Nadav], Noy, A.[Asaf], Friedman, I.[Itamar], Protter, M.[Matan], Zelnik-Manor, L.[Lihi],
Asymmetric Loss For Multi-Label Classification,
ICCV21(82-91)
IEEE DOI 2203
Training, Adaptive systems, Object detection, Benchmark testing, Complexity theory, Task analysis, Recognition and classification, Scene analysis and understanding BibRef

Peeples, J.[Joshua], McCurley, C.H.[Connor H.], Walker, S.[Sarah], Stewart, D.[Dylan], Zare, A.[Alina],
Learnable Adaptive Cosine Estimator (LACE) for Image Classification,
WACV22(3757-3767)
IEEE DOI 2202
Training, Parameter estimation, Computational modeling, Artificial neural networks, Transforms, Stability analysis, Deep Learning Object Detection/Recognition/Categorization BibRef

Yang, Z.B.[Zhi-Bo], Bastan, M.[Muhammet], Zhu, X.L.[Xin-Liang], Gray, D.[Doug], Samaras, D.[Dimitris],
Hierarchical Proxy-based Loss for Deep Metric Learning,
WACV22(449-458)
IEEE DOI 2202
Measurement, Training, Image retrieval, Clustering algorithms, Data models, Complexity theory, Object Detection/Recognition/Categorization BibRef

Ho, K.[Kalun], Keuper, J.[Janis], Pfreundt, F.J.[Franz-Josef], Keuper, M.[Margret],
Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches,
ICPR21(87-94)
IEEE DOI 2105
Correlation, Pattern recognition, Noise measurement, Convolutional neural networks, Image classification BibRef

Wang, S.[Song], Guo, X.[Xin], Tie, Y.[Yun], Qi, L.[Lin], Guan, L.[Ling],
Discriminative Patch Descriptor Learning With Focal Triplet Loss Function,
ICIP21(3567-3571)
IEEE DOI 2201
Training, Image processing, Image matching, Task analysis, Standards, triplet loss function, focal triplet loss, visual-semantic embedding learning BibRef

Zhu, Z.W.[Zhao-Wei], Liu, T.[Tongliang], Liu, Y.[Yang],
A Second-Order Approach to Learning with Instance-Dependent Label Noise,
CVPR21(10108-10118)
IEEE DOI 2111

WWW Link. Training, Deep learning, Estimation, Rendering (computer graphics), Pattern recognition, Task analysis BibRef

Liu, Y.F.[Yi-Fan], Chen, H.[Hao], Chen, Y.[Yu], Yin, W.[Wei], Shen, C.H.[Chun-Hua],
Generic Perceptual Loss for Modeling Structured Output Dependencies,
CVPR21(5420-5428)
IEEE DOI 2111
Training, Image segmentation, Image synthesis, Semantics, Superresolution, Estimation BibRef

Yang, M.X.[Mou-Xing], Li, Y.F.[Yun-Fan], Huang, Z.Y.[Zhen-Yu], Liu, Z.[Zitao], Hu, P.[Peng], Peng, X.[Xi],
Partially View-aligned Representation Learning with Noise-robust Contrastive Loss,
CVPR21(1134-1143)
IEEE DOI 2111
Robustness, Noise robustness, Spatiotemporal phenomena, Image restoration, Noise measurement, Object tracking, Object recognition BibRef

Wang, F.[Feng], Liu, H.P.[Hua-Ping],
Understanding the Behaviour of Contrastive Loss,
CVPR21(2495-2504)
IEEE DOI 2111
Temperature distribution, Computational modeling, Semantics, Temperature control, Task analysis BibRef

Draxler, F.[Felix], Schwarz, J.[Jonathan], Schnörr, C.[Christoph], Köthe, U.[Ullrich],
Characterizing the Role of a Single Coupling Layer in Affine Normalizing Flows,
GCPR20(1-14).
Springer DOI 2110
Award, GCPR, HM. BibRef

Schwarz, J.[Jonathan], Draxler, F.[Felix], Köthe, U.[Ullrich], Schnörr, C.[Christoph],
Riemannian SOS-Polynomial Normalizing Flows,
GCPR20(218-231).
Springer DOI 2110
BibRef

Kobayashi, T.[Takumi],
Group Softmax Loss with Discriminative Feature Grouping,
WACV21(2614-2623)
IEEE DOI 2106
Training, Supervised learning, Neural networks, Training data, Loss measurement BibRef

Chan, C.H.[Chi-Ho], Kittler, J.V.[Josef V.],
Angular Sparsemax for Face Recognition,
ICPR21(10473-10479)
IEEE DOI 2105
Loss function in deep networks training. Additives, Databases, Face recognition, Optimized production technology, Probability distribution, Convolutional neural networks BibRef

Bechtle, S.[Sarah], Molchanov, A.[Artem], Chebotar, Y.[Yevgen], Grefenstette, E.[Edward], Righetti, L.[Ludovic], Sukhatme, G.[Gaurav], Meier, F.[Franziska],
Meta Learning via Learned Loss,
ICPR21(4161-4168)
IEEE DOI 2105
Choosing the loss function in learning. Training, Shape, Transfer learning, Pipelines, Reinforcement learning, Tools, meta learning, deep learning BibRef

Liu, L.L.[Lan-Lan], Wang, M.Z.[Ming-Zhe], Deng, J.[Jia],
A Unified Framework of Surrogate Loss by Refactoring and Interpolation,
ECCV20(III:278-293).
Springer DOI 2012
BibRef

Zhu, Z., Wang, H.,
Deep Adversarial Active Learning With Model Uncertainty For Image Classification,
ICIP20(1711-1715)
IEEE DOI 2011
Task analysis, Uncertainty, Training, Predictive models, Data models, Labeling, Loss measurement, Active learning, Adversarial learning, Image classification BibRef

Wang, Q., Zhang, L., Wu, B., Ren, D., Li, P., Zuo, W., Hu, Q.,
What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective,
CVPR20(10768-10777)
IEEE DOI 2008
Optimization, Training, Task analysis, Convergence, Robustness, Loss measurement, Stability analysis BibRef

Cacheux, Y.L., Borgne, H.L., Crucianu, M.,
Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning,
ICCV19(10332-10341)
IEEE DOI 2004
image representation, learning (artificial intelligence), vectors, class prototypes, implicit assumptions, Covariance matrices BibRef

Zhao, X., Qi, H., Luo, R., Davis, L.,
A Weakly Supervised Adaptive Triplet Loss for Deep Metric Learning,
Fashion19(3177-3180)
IEEE DOI 2004
image retrieval, neural nets, search problems, supervised learning, deep metric learning, distance metric learning, adaptive triplet loss BibRef

Qian, Q., Shang, L., Sun, B., Hu, J., Tacoma, T., Li, H., Jin, R.,
SoftTriple Loss: Deep Metric Learning Without Triplet Sampling,
ICCV19(6449-6457)
IEEE DOI 2004
learning (artificial intelligence), neural nets, optimisation, pattern classification, sampling methods, SoftTriple loss, Data models BibRef

Yu, B., Tao, D.,
Deep Metric Learning With Tuplet Margin Loss,
ICCV19(6489-6498)
IEEE DOI 2004
learning (artificial intelligence), deep metric learning datasets, deep metric learning methods, Bars BibRef

Do, T.T.[Thanh-Toan], Tran, T.[Toan], Reid, I.D.[Ian D.], Kumar, V.[Vijay], Hoang, T.[Tuan], Carneiro, G.[Gustavo],
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning,
CVPR19(10396-10405).
IEEE DOI 2002
BibRef

Yu, B.S.[Bao-Sheng], Liu, T.L.[Tong-Liang], Gong, M.M.[Ming-Ming], Ding, C.X.[Chang-Xing], Tao, D.C.[Da-Cheng],
Correcting the Triplet Selection Bias for Triplet Loss,
ECCV18(VI: 71-86).
Springer DOI 1810
Metric learning technique. BibRef

Ge, W.F.[Wei-Feng], Huang, W.[Weilin], Dong, D.[Dengke], Scott, M.R.[Matthew R.],
Deep Metric Learning with Hierarchical Triplet Loss,
ECCV18(VI: 272-288).
Springer DOI 1810
BibRef

Wan, W.T.[Wei-Tao], Zhong, Y.Y.[Yuan-Yi], Li, T.P.[Tian-Peng], Chen, J.S.[Jian-Sheng],
Rethinking Feature Distribution for Loss Functions in Image Classification,
CVPR18(9117-9126)
IEEE DOI 1812
Training, Feature extraction, Probability distribution, Neural networks, Task analysis, Euclidean distance, Loss measurement BibRef

Qi, C., Su, F.,
Contrastive-center loss for deep neural networks,
ICIP17(2851-2855)
IEEE DOI 1803
Face recognition, Feature extraction, Neural networks, Task analysis, Testing, Training, Visualization, Auxiliary loss, Image classification and face recognition BibRef

Sajjadi, M., Javanmardi, M., Tasdizen, T.,
Mutual exclusivity loss for semi-supervised deep learning,
ICIP16(1908-1912)
IEEE DOI 1610
Entropy BibRef

Yoo, D.G.[Dong-Geun], Kweon, I.S.[In So],
Learning Loss for Active Learning,
CVPR19(93-102).
IEEE DOI 2002
BibRef

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


Last update:Dec 4, 2022 at 15:58:45