Feature Space Augmentation for Long-Tailed Data

Chu, Peng; Bian, Xiao; Liu, Shaopeng; Ling, Haibin

doi:10.1007/978-3-030-58526-6_41

Cited by 159 publications

(126 citation statements)

References 42 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…3) According to equations (10) and (11), calculate the basic probability value of the network output, and use statistical analysis to obtain the basic probability value of other evidence. 4) Use equations (5)- (8) to calculate the confidence function, likelihood function, and conflict factor K of each focal element.…”

Section: )mentioning

confidence: 99%

“…For the same reason, Figure 2 shows that the AUC area of the three models XBGboost, Rand-omForest, and BPNN after arctangent processing increased by 0.0217 on average, and the AUC area stratification occurred: the AUC area of XBGboost is larger than RandomForest, and the AUC area of RandomForest is larger than BPNN. It shows that through arctangent transformation, the input data is mapped to [0, S /2], and then normalized processing can effectively solve the long-tailed [11] distribution problem of DGA data, so that the model can better express the nonlinear relationship between input and output .…”

Section: )mentioning

confidence: 99%

“…input the reduced feature parameters into the class II XGBoost2 model, the actual output of the class II model is [0.9389, 0.0359, 0.0252], and the expected output is [1,0,0]. According to equations (10) and (11), the basic probability distribution of evidence source 3 e is calculated as [0.9363, 0.0358, 0.0251], and the basic probability distribution of another evidence source 4 e is calculated as [0.3829, 0.3160, 0.2009] based on the analysis of failure statistical data, then available Table 8: Using formulas (5)- (8) in the D-S evidence theory for fusion, the conflict factor K can be obtained as 0.4775. The confidence and likelihood of various failure types are shown in Table 9.…”

Section: Case Of Studymentioning

confidence: 99%

See 2 more Smart Citations

Transformer graded fault diagnosis based on neighborhood rough set and XGBoost

et al. 2021

View full text Add to dashboard Cite

Aiming at the uncertainty of fault type reasoning based on fault data in transformer fault diagnosis model, this paper proposed a hierarchical diagnosis model based on neighborhood rough set and XGBoost. The model used arctangent transformation to preprocess the DGA data, which could reduce the distribution span of data features and the complexity of model training. Using 5 characteristic gases and 16 gas ratios as the input characteristic parameters of the XGBoost model at all levels, reduction was performed on these 21 input feature attributes, features that had a high contribution to fault classification were retained, and redundant features were removed to improve the accuracy and efficiency of model prediction. Taking advantage of XGBoost's strong ability to extract a few features, the output of the model was the superposition of leaf node scores for each type of fault, the maximum score was the type of failure the sample belonged to, and its value was also the probability value. The obtained probability was used as one of the evidence sources to use D-S evidence theory for information fusion to verify the reliability of the model. Experiments have proved that the XGBoost graded diagnosis model proposed in this article has the highest overall accuracy rate comparing with the traditional model, reaching 93.01%, the accuracy of XGBoost models at all levels has reached more than 90%, the average accuracy rate is higher than that of the traditional model by an average of more than 2.7%, and the average time-consuming is only 0.0695 s. After D-S multi-source information fusion, the reliability of the prediction results of the model proposed in this paper has been improved.

show abstract

Section: )mentioning

confidence: 99%

Section: )mentioning

confidence: 99%

Section: Case Of Studymentioning

confidence: 99%

See 1 more Smart Citation

Transformer graded fault diagnosis based on neighborhood rough set and XGBoost

et al. 2021

View full text Add to dashboard Cite

show abstract

“…One common method is generating Gaussiandistribution-based noise directly or iteratively [5], and combine noise with data or features through linear combination [6,17]. Statisticbased methods statistics distribution of dataset to generate more controllable perturbations [2]. Gradient-based perturbation generation is another approach which based on the gradient of model's prediction loss, usually combined with gradient ascent method based on confused classes [8], adjusting method [13], and attacking methods like the Fast Gradient Sign Method (FGSM) and Project Gradient Descent (PGD) [19] [21].…”

Section: Related Work 21 Adversarial Training In Image Classificationmentioning

confidence: 99%

“…The main difference between existing adversarial training methods lies in their ways to generate and add perturbations. Commonlyused perturbation generation methods include stochastic normal distribution [17], statistical information [2], gradient [5,8,13,19,21], Generative Adversarial Networks (GAN) based methods [14]; while methods to introduce perturbations include data perturbation [5,8,13,14,19,21] and feature perturbation [2,17]. It is worth mentioning that existing methods usually make a trade-off between the model performance and robustness.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study of Adversarial Training Methods for Long-tailed Classification

Meng

et al. 2021

Proceedings of the 1st International Workshop on Adversarial Learning for Multimedia

View full text Add to dashboard Cite

Adversarial training is originated in image classification to address the problem of adversarial attacks, where an invisible perturbation in an image leads to a significant change in model decision. It recently has been observed to be effective in alleviating the long-tailed classification problem, where an imbalanced size of classes makes the model has much lower performance on small classes. However, existing methods typically focus on the methods to generate perturbations for data, while the contributions of different perturbations to long-tailed classification have not been well analyzed. To this end, this paper presents an investigation on the perturbation generation and incorporation components of existing adversarial training methods and proposes a taxonomy that defines these methods using three levels of components, in terms of information, methodology, and optimization. This taxonomy may serve as a design paradigm where an adversarial training algorithm can be created by combining different components in the taxonomy. A comparative study is conducted to verify the influence of each component in long-tailed classification. Experimental results on two benchmarking datasets show that a combination of statistical perturbations and hybrid optimization achieves a promising performance, and the gradientbased method typically improves the performance of both the head and tail classes. More importantly, it is verified that a reasonable combination of the components in our taxonomy may create an algorithm that outperforms the state-of-the-art. CCS CONCEPTS• Computing methodologies → Machine learning approaches.

show abstract

One‐stage self‐distillation guided knowledge transfer for long‐tailed visual recognition

Xia

Zhang

Wang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Deep learning has achieved remarkable progress for visual recognition on balanced data sets but still performs poorly on real‐world long‐tailed data distribution. The existing methods mainly decouple the problem into the two‐stage decoupling training, that is, representation learning and classifier training, or multistage training based on knowledge distillation, thus resulting in huge training steps and extra computation cost. In this paper, we propose a conceptually simple yet effective One‐stage Long‐tailed Self‐Distillation framework, called OLSD, which simultaneously takes representation learning and classifier training into one‐stage training. For representation learning, we take two different sampling distributions and mixup them to input them into two branches, where the collaborative consistency loss is introduced to train network consistency, and we theoretically show that the proposed mixup naturally generates a tail‐majority distribution mixup. For classifier training, we introduce balanced self‐distillation guided knowledge transfer to improve generalization performance, where we theoretically show that proposed knowledge transfer implicitly minimizes not only cross‐entropy but also KL divergence between head‐to‐tail and tail‐to‐head. Extensive experiments on long‐tailed CIFAR10/100, ImageNet‐LT and multilabel long‐tailed VOC‐LT demonstrate the proposed method's effectiveness.

show abstract

Feature Space Augmentation for Long-Tailed Data

Cited by 159 publications

References 42 publications

Transformer graded fault diagnosis based on neighborhood rough set and XGBoost

Transformer graded fault diagnosis based on neighborhood rough set and XGBoost

Comparative Study of Adversarial Training Methods for Long-tailed Classification

One‐stage self‐distillation guided knowledge transfer for long‐tailed visual recognition

Contact Info

Product

Resources

About