└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # A Survey on Small Sample Imbalanced Problem 2 | 3 | This repository provides a brief summary of methods from our review paper: A Survey on Small Sample Imbalanced Problem: Metrics, Feature Analysis, and Solutions. 4 | 5 | The small sample imbalance (S&I) problem is a major challenge in machine learning and data analysis. 6 | It is characterized by a small number of samples and an imbalanced distribution of classes, which leads to poor model performance. 7 | In addition, feature distribution and overlapping noise in the data significantly impact the classification performance. 8 | We emphasize a detailed analysis of the dataset before developing a matching solution. 9 | We first summarize imbalance metrics and complexity analysis methods that provide interpretable benchmarks for S&I. 10 | Second, we review the latest solutions for conventional, data complexity-based, and extreme S&I problems, thereby providing insights for future research. 11 | 12 | See our paper for more details. 13 | 14 | # Imbalance Measurement 15 | 16 | ## Imbalance Metrics Based on Sample Distribution 17 | 18 | - **(ID):** Measuring the class imbalance extent of multi-class problems. 19 | [[paper]](https://www.sciencedirect.com/science/article/pii/S016786551730257X) 20 | 21 | - **(LRID):** LRID: A new metric of multi-class imbalance degree based on likelihood-ratio test. 22 | [[paper]](https://openaccess.city.ac.uk/id/eprint/20447/1/Imbalance-Degree.pdf) 23 | 24 | - **(Imbalance Coefficient):** The impact of class imbalance in classification performance metrics based on the binary confusion matrix. 25 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0031320319300950) 26 | 27 | - **(RIR):** TF-IGM revisited: Imbalance text classification with relative imbalance ratio. 28 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0957417423000799) 29 | 30 | ## Measuring Imbalance with Classification Performance 31 | 32 | - **(Augmented R-value):** Dealing with overlap and imbalance: a new metric and approach. 33 | [[paper]](http://link.springer.com/10.1007/s10044-016-0583-6) 34 | 35 | - **(adjustedIR):** Adjusting the imbalance ratio by the dimensionality of imbalanced data. 36 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0167865520300829) 37 | 38 | - **(IBI3, BI3):** Bayes Imbalance Impact Index: A Measure of Class Imbalanced Data Set for Classification Problem. 39 | [[paper]](https://ieeexplore.ieee.org/document/8890005/) 40 | 41 | - **(IF):** Imbalance factor: a simple new scale for measuring inter-class imbalance extent in classification problems. 42 | [[paper]](https://link.springer.com/10.1007/s10115-023-01881-y) 43 | 44 | - **(MIR, MiCIR):** Purposive Data Augmentation Strategy and Lightweight Classification Model for Small Sample Industrial Defect Dataset. 45 | [[paper]](https://ieeexplore.ieee.org/document/10555177/) 46 | 47 | # Data Complexity Measurement 48 | 49 | - Complexity measures of supervised classification problems. 50 | [[paper]](https://ieeexplore.ieee.org/abstract/document/990132/) 51 | 52 | - Analysis of data complexity measures for classification. 53 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0957417413001413) 54 | 55 | - How Complex Is Your Classification Problem?: A Survey on Measuring Classification Complexity. 56 | [[paper]](https://dl.acm.org/doi/10.1145/3347711) 57 | [[code]](https://github.com/lpfgarcia/ECoL) 58 | 59 | - Assessing the data complexity of imbalanced datasets. 60 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0020025520311713) 61 | [[results]](https://github.com/victorhb/IS2020_results) 62 | 63 | - On the joint-effect of class imbalance and overlap: a critical review. 64 | [[paper]](https://link.springer.com/10.1007/s10462-022-10150-3) 65 | [[code: pycol]](https://github.com/miriamspsantos/pycol) 66 | [[code: open-source-imbalance-overlap]](https://github.com/miriamspsantos/open-source-imbalance-overlap) 67 | 68 | - A unifying view of class overlap and imbalance: Key concepts, multiview panorama, and open avenues for research. 69 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S1566253522001099) 70 | [[code: dcol]](https://github.com/nmacia/dcol) 71 | [[code: ImbCoL]](https://github.com/victorhb/ImbCoL) 72 | 73 | # Conventional S&I Solutions 74 | 75 | ## Data-level 76 | 77 | ### Resampling 78 | - **Synthetic Oversampling** 79 | 80 | - **(SMOTE):** SMOTE: synthetic minority over-sampling technique. 81 | [[paper]](https://www.jair.org/index.php/jair/article/view/10302/24590) 82 | [[code]](https://github.com/kaushalshetty/SMOTE) 83 | 84 | - **(Borderline-SMOTE):** Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning. 85 | [[paper]](http://link.springer.com/10.1007/11538059_91) 86 | 87 | - **(ADASYN):** ADASYN: Adaptive synthetic sampling approach for imbalanced learning. 88 | [[paper]](https://ieeexplore.ieee.org/abstract/document/4633969/) 89 | [[code]](https://github.com/stavskal/ADASYN) 90 | 91 | - **(WK-SMOTE):** Classification of Imbalanced Data by Oversampling in Kernel Space of Support Vector Machines. 92 | [[paper]](https://ieeexplore.ieee.org/document/8064210/) 93 | 94 | - **(MC-SMOTE):** Imbalanced Classification Based on Minority Clustering Synthetic Minority Oversampling Technique With Wind Turbine Fault Detection Application. 95 | [[paper]](https://ieeexplore.ieee.org/document/9302680/) 96 | 97 | - **Combined Approaches** 98 | - **(SUNDO):** A method for resampling imbalanced datasets in binary classification tasks for real-world problems. 99 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0925231213011429) 100 | 101 | - **(WRO):** An Improved Algorithm for Imbalanced Data and Small Sample Size Classification. 102 | [[paper]](http://www.scirp.org/journal/doi.aspx?DOI=10.4236/jdaip.2015.33004) 103 | 104 | ### Data augmentation 105 | - **Traditional method** 106 | - An imbalanced small sample slab defect recognition method based on image generation. 107 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S1526612524002433) 108 | 109 | - **VAE-based** 110 | - Variational autoencoder based synthetic data generation for imbalanced learning. 111 | [[paper]](https://ieeexplore.ieee.org/abstract/document/8285168/) 112 | 113 | - **(WM-CVAE):** A novel data augmentation approach to fault diagnosis with class-imbalance problem. 114 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0951832023007469) 115 | 116 | - **(TL-VAE):** Gas Path Fault Diagnosis Method Under Small Samples With Inter-Class Imbalance. 117 | [[paper]](https://asmedigitalcollection.asme.org/GT/proceedings-abstract/GT2024/87929/1203746) 118 | 119 | - **GAN-based** 120 | - **(DAC):** Data Augmentation Classifier for Imbalanced Fault Classification. 121 | [[paper]](https://ieeexplore.ieee.org/document/9115249/) 122 | 123 | - Using CGAN to Deal with Class Imbalance and Small Sample Size in Cybersecurity Problems. 124 | [[paper]](https://ieeexplore.ieee.org/document/9647807/) 125 | [[code: cgan]](https://github.com/eriklindernoren/Keras-GAN/tree/master/cgan) 126 | 127 | - **(ACGAN-SN):** A Novel Method for Fault Diagnosis of Bearings with Small and Imbalanced Data Based on Generative Adversarial Networks. 128 | [[paper]](https://www.mdpi.com/2076-3417/12/14/7346) 129 | 130 | - **(SCA-GAN):** SCA-CGAN: A New Side-Channel Attack Method for Imbalanced Small Samples. 131 | [[paper]](https://www.radioeng.cz/fulltexts/2023/23_01_0124_0135.pdf) 132 | 133 | - **(AGMAN):** Auxiliary generative mutual adversarial networks for class-imbalanced fault diagnosis under small samples. 134 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S1000936122003089) 135 | 136 | - **(ConvGeN):** ConvGeN: A convex space learning approach for deep-generative oversampling and imbalanced classification of small tabular datasets. 137 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S003132032300835X) 138 | [[code: ConvGeN]](https://github.com/kristian10007/ConvGeN) 139 | [[code: NextConvGeN]](https://github.com/kristian10007/NextConvGeN) 140 | 141 | - **Diffusion Model** 142 | - A Novel Data Augmentation Method Based on Denoising Diffusion Probabilistic Model for Fault Diagnosis Under Imbalanced Data. 143 | [[paper]](https://ieeexplore.ieee.org/document/10449886/) 144 | [[code: DDPM]](https://github.com/zoubohao/DenoisingDiffusionProbabilityModel-ddpm-) 145 | 146 | ## Algorithm-level 147 | 148 | ### Deep learning model 149 | - **(DSLWCN-VAFL):** Lightweight Network with Variable Asymmetric Rebalancing Strategy for Small and Imbalanced Fault Diagnosis. 150 | [[paper]](https://www.mdpi.com/2075-1702/10/10/879) 151 | 152 | - Transformer-Based Disease Identification for Small-Scale Imbalanced Capsule Endoscopy Dataset. 153 | [[paper]](https://www.mdpi.com/2079-9292/11/17/2747) 154 | 155 | - Wind Turbine Fault Diagnosis for Class-Imbalance and Small-Size Data Based on Stacked Capsule Autoencoder. 156 | [[paper]](https://ieeexplore.ieee.org/document/10605823/) 157 | 158 | ### Cost-sensitive learning 159 | - Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance. 160 | [[paper]](http://link.springer.com/10.1007/978-3-030-69544-6_33) 161 | [[code]](https://github.com/hitachi-rd-cv/CDB-loss) 162 | 163 | ### Ensemble learning 164 | - A novel ensemble method for classifying imbalanced data. 165 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0031320314004841) 166 | 167 | ### Transfer learning 168 | - **(Rare-Transfer):** Transfer learning for class imbalance problems with inadequate data. 169 | [[paper]](http://link.springer.com/10.1007/s10115-015-0870-3) 170 | 171 | - **(CIATL):** Class-Imbalance Adversarial Transfer Learning Network for Cross-Domain Fault Diagnosis With Imbalanced Data. 172 | [[paper]](https://ieeexplore.ieee.org/document/9655605/) 173 | 174 | - Edge–Cloud Collaboration Detection Approach for Small-Sample Imbalanced Faults in Power Lines. 175 | [[paper]](https://ieeexplore.ieee.org/document/9775087/) 176 | 177 | - **(G-TELM):** Generalized Transfer Extreme Learning Machine for Unsupervised Cross-Domain Fault Diagnosis With Small and Imbalanced Samples. 178 | [[paper]](https://ieeexplore.ieee.org/document/10142961/) 179 | 180 | ### Few-shot learning 181 | - **(PTAFedIF):** Privacy-Preserving Incipient Fault Identification in Distribution Networks Under Small Sample and Imbalanced Data Distribution Conditions. 182 | [[paper]](https://ieeexplore.ieee.org/document/10609403/) 183 | 184 | - **(TRN):** Transfer Relation Network for Fault Diagnosis of Rotating Machinery With Small Data. 185 | [[paper]](https://ieeexplore.ieee.org/document/9462541/) 186 | 187 | ## Hybrid solutions 188 | 189 | - Early Fault Detection in Induction Motors Using AdaBoost With Imbalanced Small Data and Optimized Sampling. 190 | [[paper]](http://ieeexplore.ieee.org/document/7593238/) 191 | 192 | - Exploiting Synthetically Generated Data with Semi-Supervised Learning for Small and Imbalanced Datasets. 193 | [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/4397) 194 | 195 | - A diagnosis method for imbalanced bearing data based on improved SMOTE model combined with CNN-AM. 196 | [[paper]](https://academic.oup.com/jcde/article/10/5/1930/7237474) 197 | 198 | - An oversampling method for wafer map defect pattern classification considering small and imbalanced data. 199 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0360835221006719) 200 | 201 | - DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data. 202 | [[paper]](https://ieeexplore.ieee.org/document/9694621/) 203 | [[code]](https://github.com/dd1github/DeepSMOTE) 204 | 205 | - Fault Diagnosis of Rolling Bearing with Imbalanced Small Sample Scenarios. 206 | [[paper]](https://ieeexplore.ieee.org/document/9612860/) 207 | 208 | - Deep learning approach for defective spot welds classification using small and class-imbalanced Datasets. 209 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0925231222000042) 210 | [[code]](https://github.com/daiwei9501/Defective-spot-welding) 211 | 212 | - Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification. 213 | [[paper]](https://ieeexplore.ieee.org/document/9656127/) 214 | [[code]](https://github.com/yaopengUSTC/mbit-skin-cancer.git) 215 | 216 | - Improved Generative Adversarial Network for Bearing Fault Diagnosis with a Small Number of Data and Unbalanced Data. 217 | [[paper]](https://www.mdpi.com/2073-8994/16/3/358) 218 | 219 | - Imbalanced fault diagnosis of rotating machinery via multi-domain feature extraction and cost-sensitive learning. 220 | [[paper]](http://link.springer.com/10.1007/s10845-019-01522-8) 221 | 222 | - Convolution-GRU Based on Independent Component Analysis for fMRI Analysis with Small and Imbalanced Samples. 223 | [[paper]](https://www.mdpi.com/2076-3417/10/21/7465) 224 | 225 | - Automated Traffic Incident Detection: Coping With Imbalanced and Small Datasets. 226 | [[paper]](https://ieeexplore.ieee.org/document/9740116/) 227 | 228 | - Pedestrian gender classification on imbalanced and small sample datasets using deep and traditional features. 229 | [[paper]](https://link.springer.com/10.1007/s00521-023-08331-4) 230 | 231 | - A novel building heat pump system semi-supervised fault detection and diagnosis method under small and imbalanced data. 232 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0952197623005006) 233 | 234 | - Classification of autonomous vehicle crash severity: Solving the problems of imbalanced datasets and small sample size. 235 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0001457524002112) 236 | 237 | # Data Complexity Solutions for S&I 238 | 239 | ## Data-level 240 | 241 | ### Resampling 242 | - **Filtering-Based** 243 | 244 | - **(SMOTE-Tomek, SMOTE-ENN):** A study of the behavior of several methods for balancing machine learning training data. 245 | [[paper]](https://dl.acm.org/doi/10.1145/1007730.1007735) 246 | [[code: SMOTE_TomekLinks]](https://github.com/karollukawski/SMOTE_TomekLinks) 247 | [[code: SMOTE-ENN]](https://github.com/Hilmahna/SMOTE-ENN) 248 | 249 | - **(SMOTE-IPF):** SMOTE–IPF: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering. 250 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0020025514008561) 251 | 252 | - **(SMOTE-WENN):** SMOTE-WENN: Solving class imbalance and small sample problems by oversampling and distance scaling. 253 | [[paper]](https://link.springer.com/10.1007/s10489-020-01852-8) 254 | 255 | - **Feature-Based** 256 | - **(FW-SMOTE):** FW-SMOTE: A feature-weighted oversampling approach for imbalanced classification. 257 | [[paper]](https://www.sciencedirect.com/science/article/abs/pii/S0031320321006877) 258 | 259 | - **Sample Concatenation** 260 | - **(Re-SC):** Resampling algorithms based on sample concatenation for imbalance learning. 261 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0950705122002659) 262 | 263 | - **Clustering + Weighting** 264 | - **(A-SUWO):** Adaptive semi-unsupervised weighted oversampling (A-SUWO) for imbalanced datasets. 265 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0957417415007356) 266 | 267 | - **(IA-SUWO):** IA-SUWO: An Improving Adaptive semi-unsupervised weighted oversampling for imbalanced classification problems. 268 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0950705120303804) 269 | 270 | - **(MWMOTE):** MWMOTE–Majority Weighted Minority Oversampling Technique for Imbalanced Data Set Learning 271 | [[paper]](https://ieeexplore.ieee.org/document/6361394/?arnumber=6361394) 272 | [[code]](https://github.com/oncoyne/MWMOTE) 273 | 274 | - **(NI-MWMOTE):** NI-MWMOTE: An improving noise-immunity majority weighted minority oversampling technique for imbalanced classification problems. 275 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0957417420303286) 276 | 277 | - **(IMWMOTE):** IMWMOTE: A novel oversampling technique for fault diagnosis in heterogeneous imbalanced data. 278 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0957417424008534) 279 | 280 | - **(EM-LWMOTE):** A Local Adaptive Minority Selection and Oversampling Method for Class-Imbalanced Fault Diagnostics in Industrial Systems. 281 | [[paper]](https://ieeexplore.ieee.org/document/8897117/) 282 | 283 | - **Cleaning-Based** 284 | - **(CCR):** CCR: A combined cleaning and resampling algorithm for imbalanced data classification. 285 | [[paper]](https://sciendo.com/article/10.1515/amcs-2017-0050) 286 | [[code]](https://github.com/michalkoziarski/CCR) 287 | 288 | - **(MC-CCR):** Combined cleaning and resampling algorithm for multi-class imbalanced data with label noise. 289 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0950705120304330) 290 | [[code]](https://github.com/michalkoziarski/MC-CCR) 291 | 292 | - **(RB-CCR):** RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification. 293 | [[paper]](https://link.springer.com/10.1007/s10994-021-06012-8) 294 | [[code]](https://github.com/michalkoziarski/RB-CCR) 295 | 296 | - **Radial-Based** 297 | - **(RBO):** Radial-Based oversampling for noisy imbalanced data classification. 298 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0925231219301596) 299 | [[code]](https://github.com/michalkoziarski/RBO) 300 | 301 | - **(MC-RBO):** Radial-Based Oversampling for Multiclass Imbalanced Data Classification. 302 | [[paper]](https://ieeexplore.ieee.org/document/8743475/?arnumber=8743475) 303 | [[code]](https://github.com/michalkoziarski/MultiClassRBO) 304 | 305 | - **Distance-based** 306 | - **(MDO):** To Combat Multi-Class Imbalanced Problems by Means of Over-Sampling Techniques. 307 | [[paper]](https://ieeexplore.ieee.org/document/7163639) 308 | 309 | - **(AMDO):** AMDO: An Over-Sampling Technique for Multi-Class Imbalanced Problems. 310 | [[paper]](https://ieeexplore.ieee.org/document/8065074/) 311 | 312 | ### Data augmentation 313 | - **(MoGAN):** Oversampling adversarial network for class-imbalanced fault diagnosis. 314 | [[paper]](https://www.sciencedirect.com/science/article/pii/S0888327020305616) 315 | 316 | - **(FAWGAN-GN):** Full Attention Wasserstein GAN With Gradient Normalization for Fault Diagnosis Under Imbalanced Data. 317 | [[paper]](https://ieeexplore.ieee.org/abstract/document/9829874) 318 | 319 | - **(PCWGAN-GP):** PCWGAN-GP: A New Method for Imbalanced Fault Diagnosis of Machines. 320 | [[paper]](https://ieeexplore.ieee.org/document/9789104/) 321 | 322 | - **(CFGAN):** Categorical Feature GAN for Imbalanced Intelligent Fault Diagnosis of Rotating Machinery. 323 | [[paper]](https://ieeexplore.ieee.org/abstract/document/10192450) 324 | 325 | ## Feature-level 326 | 327 | - **(S2N and FAST):** Combating the Small Sample Class Imbalance Problem Using Feature Selection. 328 | [[paper]](https://ieeexplore.ieee.org/abstract/document/5276797) 329 | 330 | - **(AMF):** Feature Selection Metric Using AUC Margin for Small Samples and Imbalanced Data Classification Problems. 331 | [[paper]](http://ieeexplore.ieee.org/document/6146959/) 332 | 333 | - **(DBFS):** DBFS: An effective Density Based Feature Selection scheme for small sample size and high dimensional imbalanced data sets. 334 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0169023X12000821) 335 | 336 | - **(UIG-CFGVM):** A Hybrid Feature Selection Algorithm Applied to High-dimensional Imbalanced Small-sample Data Classification. 337 | [[paper]](https://ieeexplore.ieee.org/document/9023210/) 338 | 339 | - **(MOSNS and MOSS):** Feature selection and classification by minimizing overlap degree for class-imbalanced data in metabolomics. 340 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0169743919306070) 341 | 342 | ## Algorithm-level 343 | 344 | - **(Soft-Hybrid):** Improving classification rate constrained to imbalanced data between overlapped and non-overlapped regions by hybrid algorithms. 345 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0925231214012788) 346 | 347 | - **(Meta-learning):** Learning to Reweight Examples for Robust Deep Learning. 348 | [[paper]](https://proceedings.mlr.press/v80/ren18a.html) 349 | 350 | - **(Class-Balanced loss):** Class-balanced loss based on effective number of samples. 351 | [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Cui_Class-Balanced_Loss_Based_on_Effective_Number_of_Samples_CVPR_2019_paper.html) 352 | [[code]](https://github.com/richardaecn/class-balanced-loss) 353 | 354 | - **(RBBag):** Roughly balanced bagging for imbalanced data. 355 | [[paper]](https://onlinelibrary.wiley.com/doi/10.1002/sam.10061) 356 | 357 | - **(RBBag+RSM and MRBBag):** Multi-class and feature selection extensions of Roughly Balanced Bagging for imbalanced data. 358 | [[paper]](http://link.springer.com/10.1007/s10844-017-0446-7) 359 | 360 | ## Hybrid solutions 361 | 362 | - **(WMODA):** Imbalanced data fault diagnosis of rotating machinery using synthetic oversampling and feature learning 363 | [[paper]](https://www.sciencedirect.com/science/article/pii/S027861251830044X) 364 | 365 | - **(PCA-SMOTE-SVM):** Chiller fault diagnosis with field sensors using the technology of imbalanced data. 366 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S1359431119304314) 367 | 368 | - Combining feature selection and hybrid approach redefinition in handling class imbalance and overlapping for multi-class imbalanced. 369 | [[paper]](http://ijeecs.iaescore.com/index.php/IJEECS/article/view/23872) 370 | 371 | - A Weakly Supervised Learning-Based Oversampling Framework for Class-Imbalanced Fault Diagnosis. 372 | [[paper]](https://ieeexplore.ieee.org/abstract/document/9677063) 373 | [[code]](https://github.com/qm19/A-Weakly-Supervised-Learning-based-Oversampling-Framework-for-Imbalanced-Classification) 374 | 375 | - An Ensemble Resampling Based Transfer AdaBoost Algorithm for Small Sample Credit Classification with Class Imbalance. 376 | [[paper]](https://link.springer.com/10.1007/s10614-024-10690-6) 377 | 378 | - New imbalanced fault diagnosis framework based on Cluster-MWMOTE and MFO-optimized LS-SVM using limited and complex bearing data. 379 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0952197620302773) 380 | 381 | - New imbalanced bearing fault diagnosis method based on Sample-characteristic Oversampling TechniquE (SCOTE) and multi-class LS-SVM. 382 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S1568494620309819) 383 | 384 | - Novel extended NI-MWMOTE-based fault diagnosis method for data-limited and noise-imbalanced scenarios. 385 | [[paper]](https://linkinghub.elsevier.com/retrieve/pii/S0957417423023011) 386 | 387 | # Extreme S&I Solutions 388 | 389 | - **(SWIM):** Synthetic Oversampling with the Majority Class: A New Perspective on Handling Extreme Imbalance. 390 | [[paper]](https://ieeexplore.ieee.org/document/8594869/?arnumber=8594869) 391 | 392 | - **(Few-shot GAN):** Few-Shot GAN: Improving the Performance of Intelligent Fault Diagnosis in Severe Data Imbalance. 393 | [[paper]](https://ieeexplore.ieee.org/document/10121392/) 394 | 395 | - **(UCML):** Multiset Feature Learning for Highly Imbalanced Data Classification. 396 | [[paper]](https://ieeexplore.ieee.org/document/8765367/) 397 | 398 | - **(DSADRSViT-IIRL):** Residual Shrinkage ViT with Discriminative Rebalancing Strategy for Small and Imbalanced Fault Diagnosis. 399 | [[paper]](https://www.mdpi.com/1424-8220/24/3/890) 400 | 401 | ## Long-tail distribution 402 | 403 | - **(IFL):** Invariant Feature Learning for Generalized Long-Tailed Classification. 404 | [[paper]](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840698.pdf) 405 | [[code]](https://github.com/KaihuaTang/Generalized-Long-Tailed-Benchmarks.pytorch) 406 | 407 | - **(RCAL):** When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method. 408 | [[paper]](https://ieeexplore.ieee.org/document/10376916/) 409 | 410 | - **(ProLT):** Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning. 411 | [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/28026) 412 | 413 | - **(DO):** Decoupled Optimisation for Long-Tailed Visual Recognition. 414 | [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/27902) 415 | 416 | - **(ProCo):** Probabilistic Contrastive Learning for Long-Tailed Visual Recognition. 417 | [[paper]](https://ieeexplore.ieee.org/document/10444057/) 418 | [[code]](https://github.com/LeapLabTHU/ProCo) 419 | 420 | # Contact 421 | If you have any suggestions or find our work helpful, feel free to contact us. 422 | 423 | Email: {guijie,zhaosxian}@seu.edu.cn 424 | --------------------------------------------------------------------------------