A Nonuniform Weighted Loss Function for Imbalanced Image Classification

Qiu, Qiang; Song, Zichen

doi:10.1145/3191442.3191458

Cited by 9 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While standard techniques like data augmentation and weighted loss function [ 60 ] can sometimes be used to correct the imbalanced data distributions, they are not applicable in all situations. In our experiments, data augmentation and weighted loss function do not enrich our model, which is not unexpected.…”

Section: Empirical Evaluationmentioning

confidence: 99%

RLMD‐PA: A Reinforcement Learning‐Based Myocarditis Diagnosis Combined with a Population‐Based Algorithm for Pretraining Weights

Moravvej

Alizadehsani

Khanam

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Myocarditis is heart muscle inflammation that is becoming more prevalent these days, especially with the prevalence of COVID-19. Noninvasive imaging cardiac magnetic resonance (CMR) can be used to diagnose myocarditis, but the interpretation is time-consuming and requires expert physicians. Computer-aided diagnostic systems can facilitate the automatic screening of CMR images for triage. This paper presents an automatic model for myocarditis classification based on a deep reinforcement learning approach called as reinforcement learning-based myocarditis diagnosis combined with population-based algorithm (RLMD-PA) that we evaluated using the Z-Alizadeh Sani myocarditis dataset of CMR images prospectively acquired at Omid Hospital, Tehran. This model addresses the imbalanced classification problem inherent to the CMR dataset and formulates the classification problem as a sequential decision-making process. The policy of architecture is based on convolutional neural network (CNN). To implement this model, we first apply the artificial bee colony (ABC) algorithm to obtain initial values for RLMD-PA weights. Next, the agent receives a sample at each step and classifies it. For each classification act, the agent gets a reward from the environment in which the reward of the minority class is greater than the reward of the majority class. Eventually, the agent finds an optimal policy under the guidance of a particular reward function and a helpful learning environment. Experimental results based on standard performance metrics show that RLMD-PA has achieved high accuracy for myocarditis classification, indicating that the proposed model is suitable for myocarditis diagnosis.

show abstract

Section: Empirical Evaluationmentioning

confidence: 99%

RLMD‐PA: A Reinforcement Learning‐Based Myocarditis Diagnosis Combined with a Population‐Based Algorithm for Pretraining Weights

Moravvej

Alizadehsani

Khanam

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…Possible solutions for handling the long-tailed distribution include modification of the data distribution 1 and adjustment of reasonable costs to reweight class errors. 2,3 However, the existing data-level approaches are prone to overfitting, whereas existing cost-sensitive learning methods require a careful choice of weights. As discussed by Fort et al, 4 these approaches have not performed well in rare conditions.…”

Section: Introductionmentioning

confidence: 99%

Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images

Rezaei,

Näppi,

Bischl

et al. 2023

J. Med. Imag.

View full text Add to dashboard Cite

.PurposeDeep supervised learning provides an effective approach for developing robust models for various computer-aided diagnosis tasks. However, there is often an underlying assumption that the frequencies of the samples between the different classes of the training dataset are either similar or balanced. In real-world medical data, the samples of positive classes often occur too infrequently to satisfy this assumption. Thus, there is an unmet need for deep-learning systems that can automatically identify and adapt to the real-world conditions of imbalanced data.ApproachWe propose a deep Bayesian ensemble learning framework to address the representation learning problem of long-tailed and out-of-distribution (OOD) samples when training from medical images. By estimating the relative uncertainties of the input data, our framework can adapt to imbalanced data for learning generalizable classifiers. We trained and tested our framework on four public medical imaging datasets with various imbalance ratios and imaging modalities across three different learning tasks: semantic medical image segmentation, OOD detection, and in-domain generalization. We compared the performance of our framework with those of state-of-the-art comparator methods.ResultsOur proposed framework outperformed the comparator models significantly across all performance metrics (pairwise t-test: p < 0.01) in the semantic segmentation of high-resolution CT and MR images as well as in the detection of OOD samples (p < 0.01), thereby showing significant improvement in handling the associated long-tailed data distribution. The results of the in-domain generalization also indicated that our framework can enhance the prediction of retinal glaucoma, contributing to clinical decision-making processes.ConclusionsTraining of the proposed deep Bayesian ensemble learning framework with dynamic Monte-Carlo dropout and a combination of losses yielded the best generalization to unseen samples from imbalanced medical imaging datasets across different learning tasks.

show abstract

“…The overall structure of the network is complex, requires high hardware resources, and the detection speed is slow. In order to better deploy the object detection algorithm on UAV-related embedded equipment, Zhang et al proposed the Slim YOLOv3 [39] algorithm, which was tested on the VisDrone 2018 [10] object detection test set, and the detection accuracy of the algorithm was comparable to that of YOLOv3 [40] [23], the number of parameters of the network was reduced by 92%, and the detection speed was increased by two times. In 2021, Piciarelli et al proposed an algorithm for real-time tracking and detection of multi-scale targets [2], and experimental results show that its performance reaches the most advanced algorithm performance.…”

Section: Introductionmentioning

confidence: 99%

Adaptive clustering object detection method for UAV images under long-tailed distributions

Li,

Wang,

et al. 2023

ITC

View full text Add to dashboard Cite

UAV images are characterized by small targets, difficult to identify in the background image, clustering and sparse distribution of targets, etc. Many researchers have proposed the clustering target detection method (ClusDet) for UAV images. However, due to the large differences in target scales and uneven distribution of targets in UAV images, showing long-tailed distribution, the traditional ClusDet algorithm tends to truncate large and medium targets in the process of clustering; in the detection process, the fixed-threshold NMS method in the ClusDet algorithm is difficult to adaptively detect targets of different sizes, clustering and mutual occlusion. To address the above problems, this paper proposes an adaptive clustered target detection algorithm based on UAV images under long-tail distribution. The method is divided into three sub-networks: the adaptive clustering sub-network, which outputs several segmented images of small target clustering regions by extracting potential small target clustering regions in UAV aerial images; the segmentation and filling sub-network, which fills the images with disproportionate aspect ratio for the output of the adaptive clustering network to keep the size of the images within the reasonable range required by the detection network; and the detection sub-network, which detects the targets within the reasonable range required by the detection network by introducing attention mechanism, using variable threshold NMS, and training using sample balancing strategy effectively improve the detection accuracy of targets in the clustered region. Trained in VisDrone 2019 dataset, the simulation results show that the UAV image adaptive clustering target detection method based on long-tailed distribution has a large improvement in the detection accuracy of small targets, and can effectively improve the detection accuracy of the model for targets in the aggregation region, while the model has good generalization ability.

show abstract

A Nonuniform Weighted Loss Function for Imbalanced Image Classification

Cited by 9 publications

References 12 publications

RLMD‐PA: A Reinforcement Learning‐Based Myocarditis Diagnosis Combined with a Population‐Based Algorithm for Pretraining Weights

RLMD‐PA: A Reinforcement Learning‐Based Myocarditis Diagnosis Combined with a Population‐Based Algorithm for Pretraining Weights

Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images

Adaptive clustering object detection method for UAV images under long-tailed distributions

Contact Info

Product

Resources

About