Imbalanced image classification with complement cross entropy

Kim, Yechan; Lee, Younkwan; Jeon, Moongu

doi:10.1016/j.patrec.2021.07.017

Cited by 58 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The loss function is the main part of training a neural network model and is used to adjust the weights of the neural network [60]. As a result of processing training examples by a neural network, output responses are generated that indicate the probability or reliability of possible categories to which the analyzed data belong [61]. The resulting probabilities are compared with the true labels.…”

Section: Modification Of the Cross-entropy Loss Function Using Weight...mentioning

confidence: 99%

Multimodal Neural Network System for Skin Cancer Recognition with a Modified Cross-Entropy Loss Function

Lyakhov¹,

Lyakhova²,

Kalita³

2023

Preprint

View full text Add to dashboard Cite

Currently, skin cancer is the most commonly diagnosed form of cancer in humans and is one of the leading causes of death in patients with cancer. Biopsy methods are an invasive research method and are not always available for primary diagnosis. Imaging methods have low accuracy and depend on the experience of the dermatologist. Artificial intelligence technologies can match and surpass visual analysis methods in accuracy, but they have the risk of a false negative response when a malignant pigmented lesion can be recognized as benign. One possible way to improve accuracy and reduce the risk of false negatives is to analyze heterogeneous data, combine different preprocessing methods, and use modified loss functions to eliminate the negative impact of unbalanced dermatological data. The paper proposes a multimodal neural network system with a modified cross-entropy loss function that is sensitive to unbalanced heterogeneous dermatological data. The accuracy of recognition in 10 diagnostically significant categories for the proposed system was 85.19%. The novelty of the proposed system lies in the use of cross-entropy loss when training the modified function with the help of weight coefficients. The introduction of weighting factors has reduced the number of false negative forecasts, as well as improved accuracy by 1.02-4.03 percentage points compared to the original multimodal systems. The introduction of the proposed multimodal system as an auxiliary diagnostic tool can reduce the consumption of financial and labor resources involved in the medical industry, as well as increase the chance of early detection of skin cancer.

show abstract

Section: Modification Of the Cross-entropy Loss Function Using Weight...mentioning

confidence: 99%

Multimodal Neural Network System for Skin Cancer Recognition with a Modified Cross-Entropy Loss Function

Lyakhov¹,

Lyakhova²,

Kalita³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For classification sub-networks (g cls and h cls ) and localization sub-networks (g loc and h loc ), a fully convolutional network is employed, consisting of four times 3 × 3 on 256 feature size convolutional layers with the same padding and PReLU [52] activation. Each sub-network is trained with CCE loss [56] for classification and L1 smooth loss [2] for 4-axis box coordinates regression. The experimental results are presented in the following sections.…”

Section: A Implementation Detailsmentioning

confidence: 99%

License Plate Detection via Information Maximization

Lee

Jeon

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

License plate (LP) detection in the wild remains challenging due to the diversity of environmental conditions. Nevertheless, prior solutions have focused on controlled environments, such as when LP images frequently emerge as from an approximately frontal viewpoint and without scene text which might be mistaken for an LP. However, even for stateof-the-art object detectors, their detection performance is not satisfactory for real-world environments, suffering from various types of degradation. To solve these problems, we propose a novel end-to-end framework for robust LP detection, designed for such challenging settings. Our contribution is threefold: (1) A novel information-theoretic learning that takes advantage of a shared encoder, an LP detector and a scene text detector (excluding LP) simultaneously; (2) Localization refinement for generalizing the bounding box regression network to complement ambiguous detection results; (3) a large-scale, comprehensive dataset, LPST-110K, representing real-world unconstrained scenes including scene text annotations. Computational tests show that the proposed model outperforms other state-of-theart methods on a variety of challenging datasets.

show abstract

“…In 2019, Cui et al [ 18 ] proposed the class-balanced loss framework, using the effective number of samples per class to inversely weight the loss, and this method can effectively solve the class number imbalance problem. Kim et al [ 19 ] proposed complement cross-entropy (CCE) to solve the problem of imbalanced classification and proved that suppressing the probability of the error class helps the deep learning model to learn discriminative information. By neutralizing the confidence of the error sample, the minority class samples get more learning opportunities.…”

Section: Problem Statement and Backgroundmentioning

confidence: 99%

Double-Balanced Loss for Imbalanced Colorectal Lesion Classification

Wei

Xiong

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Colorectal cancer has a high incidence rate in all countries around the world, and the survival rate of patients is improved by early detection. With the development of object detection technology based on deep learning, computer-aided diagnosis of colonoscopy medical images becomes a reality, which can effectively reduce the occurrence of missed diagnosis and misdiagnosis. In medical image recognition, the assumption that training samples follow independent identical distribution (IID) is the key to the high accuracy of deep learning. However, the classification of medical images is unbalanced in most cases. This paper proposes a new loss function named the double-balanced loss function for the deep learning model, to improve the impact of datasets on classification accuracy. It introduces the effects of sample size and sample difficulty to the loss calculation and deals with both sample size imbalance and sample difficulty imbalance. And it combines with deep learning to build the medical diagnosis model for colorectal cancer. Experimentally verified by three colorectal white-light endoscopic image datasets, the double-balanced loss function proposed in this paper has better performance on the imbalance classification problem of colorectal medical images.

show abstract

Imbalanced image classification with complement cross entropy

Cited by 58 publications

References 14 publications

Multimodal Neural Network System for Skin Cancer Recognition with a Modified Cross-Entropy Loss Function

Multimodal Neural Network System for Skin Cancer Recognition with a Modified Cross-Entropy Loss Function

License Plate Detection via Information Maximization

Double-Balanced Loss for Imbalanced Colorectal Lesion Classification

Contact Info

Product

Resources

About