CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

Shu, Jun; Yuan, Xiang; Meng, Deyu; Xu, Zongben

doi:10.1109/tpami.2023.3271451

Cited by 23 publications

(25 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method in Reference 12 reproduced nearly all of the prominent techniques for fine‐grained classification using webly supervised learning: NEIL, 67 WSDG, 68 Sukhbaatar et al, 69 Bergamo et al, 26 Xiao et al 70 In addition, we also directly utilize the performances of Decoupling 22 and Co‐teaching 23 on CUB200‐2011 dataset from Reference 71. The test accuracy of CMW‐Net‐SL 73 is reported and we rerun the code of SELC 72 for comparison.…”

Section: Methodsmentioning

confidence: 99%

Robust fine‐grained visual recognition with images based on internet of things

Cai,

Yan,

Huang

2024

Computational Intelligence

View full text Add to dashboard Cite

Labeling fine‐grained objects manually is extremely challenging, as it is not only label‐intensive but also requires professional knowledge. Accordingly, robust learning methods for fine‐grained recognition with web images collected from Internet of Things have drawn significant attention. However, training deep fine‐grained models directly using untrusted web images is confronted by two primary obstacles: (1) label noise in web images and (2) domain variance between the online sources and test datasets. To this end, in this study, we mainly focus on addressing these two pivotal problems associated with untrusted web images. To be specific, we introduce an end‐to‐end network that collaboratively addresses these concerns in the process of separating trusted data from untrusted web images. To validate the efficacy of our proposed model, untrusted web images are first collected by utilizing the text category labels found within fine‐grained datasets. Subsequently, we employ the designed deep model to eliminate label noise and ameliorate domain mismatch. And the chosen trusted web data are utilized for model training. Comprehensive experiments and ablation studies validate that our method consistently surpasses other state‐of‐the‐art approaches for fine‐grained recognition tasks in real‐world scenarios, demonstrating a significant improvement margin (2.51% on CUB200‐2011 and 2.92% on Stanford Dogs). The source code and models can be accessed at: https://github.com/Codeczh/FGVC‐IoT.

show abstract

Section: Methodsmentioning

confidence: 99%

Robust fine‐grained visual recognition with images based on internet of things

Cai,

Yan,

Huang

2024

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Much research has been done on the class-imbalance problem [15][16][17][18][19][20]40], and different solutions have been proposed to solve this problem including under-sampling and over-sampling [41,42], reconciliation of loss function [15,17,43,44], and learning paradigms such as self-supervised learning [16,45], transfer learning [18], ensemble learning [46,47], metalearning [48], and metric learning [49]. All these methods have been used in the scenario of a single domain and use the data splits for all participants from the same domain, while we extend the data heterogeneity problem to multi-domain and imbalance classes in FL environment.…”

Section: Related Work 21 Class-imbalance and Label Distributionmentioning

confidence: 99%

Exploiting data diversity in multi-domain federated learning

Ahmad Madni,

Muhammad Umer,

Luca Foresti

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Federated Learning (FL) is an evolving machine learning technique that allows collaborative model training without sharing the original data among participants. In real-world scenarios, data residing at multiple clients are often heterogeneous in terms of different resolutions, magnifications, scanners, or imaging protocols, and thus challenging for global FL model convergence in collaborative training. Most of the existing FL methods consider data heterogeneity within one domain by assuming same data variation in each client site. In this paper, we consider data heterogeneity in FL with different domains of heterogeneous data by raising the problems of domain-shift, class-imbalance, and missing data. We propose a method, MDFL (Multi-Domain Federated Learning) as a solution to heterogeneous training data from multiple domains by training robust Transformer model. We use two loss functions, one for correctly predicting class labels and other for encouraging similarity and dissimilarity over latent features, to optimize the global FL model. We perform various experiments using different convolution-based networks and non-convolutional Transformer architectures on multi-domain datasets. We evaluate the proposed approach on benchmark datasets and compare with the existing FL methods. Our results show the superiority of the proposed approach which performs better in term of robust FL global model than the exiting methods.

show abstract

“…In the training process, when there is a significant disparity between positive and negative samples, the model tends to pay more attention to the majority samples that have a higher frequency of occurrence. 30 So, the representation of minority classes was not learned enough, and the model was more inclined to predict the majority classes and ignore the minority classes. It might lead to the poor classification effect of the model on minority classes.…”

Section: Journal Of Chemical Information and Modelingmentioning

confidence: 99%

Prediction of Cytochrome P450 Inhibition Using a Deep Learning Approach and Substructure Pattern Recognition

Chen,

Zhang,

Zhang

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Cytochrome P450 (CYP) is a family of enzymes that are responsible for about 75% of all metabolic reactions. Among them, CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4 participate in the metabolism of most drugs and mediate many adverse drug reactions. Therefore, it is necessary to estimate the chemical inhibition of Cytochrome P450 enzymes in drug discovery and the food industry. In the past few decades, many computational models have been reported, and some provided good performance. However, there are still several issues that should be resolved for these models, such as single isoform, models with unbalanced performance, lack of structural characteristics analysis, and poor availability. In the present study, the deep learning models based on python using the Keras framework and TensorFlow were developed for the chemical inhibition of each CYP isoform. These models were established based on a large data set containing 85715 compounds extracted from the PubChem bioassay database. On external validation, the models provided good AUC values with 0.97, 0.94, 0.94, 0.96, and 0.94 for CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4, respectively. The models can be freely accessed on the Web server named CYPi-DNNpredictor (cypi.sapredictor.cn), and the codes for the model were made open source in the Supporting Information. In addition, we also analyzed the structural characteristics of chemicals with CYP450 inhibition and detected the structural alerts (SAs), which should be responsible for the inhibition. The SAs were also made available online, named CYPi-SAdetector (cypisa.sapredictor.cn). The models can be used as a powerful tool for the prediction of CYP450 inhibitors, and the SAs should provide useful information for the mechanisms of Cytochrome P450 inhibition.

show abstract

CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

Cited by 23 publications

References 43 publications

Robust fine‐grained visual recognition with images based on internet of things

Robust fine‐grained visual recognition with images based on internet of things

Exploiting data diversity in multi-domain federated learning

Prediction of Cytochrome P450 Inhibition Using a Deep Learning Approach and Substructure Pattern Recognition

Contact Info

Product

Resources

About