Sample Specific Generalized Cross Entropy for Robust Histology Image Classification

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate approach would be to look for loss functions that are inherently noise-tolerant. For binary classification there exist theoretical results on loss functions that are robust to label noise. In this paper, we provide some sufficient conditions on a loss function so that risk minimization under that loss function would be inherently tolerant to label noise for multiclass classification problems. These results generalize the existing results on noise-tolerant loss functions for binary classification. We study some of the widely used loss functions in deep networks and show that the loss function based on mean absolute value of error is inherently robust to label noise. Thus standard back propagation is enough to learn the true classifier even under label noise. Through experiments, we illustrate the robustness of risk minimization with such loss functions for learning neural networks.

Corrosion is a natural phenomenon that causes significant material and economic losses. Timely inspection of corroded assets is vital for preventing such losses. Visual inspection is a non-destructive method that is commonly used for corrosion detection. The ability of deep learning methods to capture corrosion visual information allows for the automation of the manual inspection process. The literature includes several examples of deep learning models to detect metal corrosion. In developing such models, loss functions are crucial and directly influence the models’ performance. Although cross-entropy is a commonly used objective function for corrosion detection, systematic evaluation of alternative loss functions—and the performance gains they may unlock—has been largely neglected. This study uses eight loss functions, namely, cross-entropy loss, Focal loss, Unified Focal loss, Dice loss, Tversky loss, Focal Tversky loss, Combo loss, and Hybrid Focal loss, to train UNet-based models for corrosion segmentation and compares their performance. The results demonstrated that the model trained with the Dice loss achieved higher performance, with a mean Jaccard index value of 64.28%, while the Focal loss exhibited the lowest performance, with a mean Jaccard value of 57.20%. This study contributes to academia and practice by demonstrating the performance gains that can be achieved by tweaking the deep learning models using optimal loss functions. • Corrosion is a phenomenon that considerably impacts the environment and economy. • Deep learning models can be trained for corrosion detection, and loss functions are essential to developing accurate models. • This study evaluates the use of different loss functions, including the Focal loss, Unified Focal loss, Dice loss, Tversky loss, Focal Tversky loss, Combo loss, and Hybrid Focal loss, to train UNet-based models for corrosion segmentation. • On a standard dataset, the models developed with Combo loss, Tversky loss, Unified Focal loss, and Dice loss had higher performance than those developed with cross-entropy loss. • With the hyperparameter tuning, higher performance gains can be achieved.

Contrastive learning of graphs under label noise

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision. In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by the Active Shape Model (ASM), is ASM Loss, designed to improve the detection of facial landmarks and head pose accuracy in facial images. Additionally, influenced by Knowledge Distillation (KD), I introduce KD-Loss, a loss designed specifically for regression tasks, focusing on detecting facial landmarks. Proceeding to the second phase of my research, I focus on regression problems. Building upon my prior work, I introduce Adaptive Coordinate-based Regression (ACR)-Loss, a context-aware loss function with face alignment implication. I provide a mechanism to dynamically measure how hard the localization of each landmark point is, and accordingly, ACR-Loss provides unique feedback to the model. Furthermore, I introduce Intensity-aware Categorical (IC)-Loss for detecting sagittal cervical spine landmark points in medical images. It effectively deploys characteristics from classification problems to enhance regression optimization. Both ACR-Loss and IC-Loss comprise contextual information, leading to a significant enhancement in localization precision. In the third phase, I turned my attention toward classification problems within the domain of deep machine learning. I introduce Adaptive Correlation-based (Ad-corre) Loss, designed to enhance the discriminative capabilities of deep learning models, with a specific focus on improving classification accuracy in automatic facial expression recognition. Furthermore, I introduce Informative (Info) Loss, a specialized loss function developed for medical applications, specifically aimed at distinguishing between Mild Cognitive Impairment and Normal Cognition groups based on transcriptions of interviews conducted as part of the I-CONECT study. Overall, I have proposed custom loss functions to improve the predictive performance in both regression and classification problems. Furthermore, I have introduced assistive loss functions, designed to enhance the performance of the main loss functions. The collective outcomes of this extensive exploration highlight the critical role of loss functions, adapting and optimizing them for various domains in deep machine learning. This research suggests and proposes a variety of methodologies for designing adaptive and context-aware loss functions within deep machine learning.

Sea turtles exhibit high migratory rates and occupy a broad range of habitats, which in turn makes monitoring these taxa challenging. Applying deep learning (DL) models to vast image datasets collected from citizen science programs can offer promising solutions to overcome the challenge of monitoring the wide habitats of wildlife, particularly sea turtles. Among DL models, object detection models, such as the You Only Look Once (YOLO) series, have been extensively employed for wildlife classification. Despite their successful application in this domain, detecting objects in images with complex backgrounds, including underwater environments, remains a significant challenge. Recently, instance segmentation models have been developed to address this issue by providing more accurate classification of complex images compared to traditional object detection models. This study compared the performance of two state-of-the-art DL methods namely; the object detection model (YOLOv5) and instance segmentation model (YOLOv5-seg), to detect and classify sea turtles. The images were collected from iNaturalist and Google and then divided into 64% for training, 16% for validation, and 20% for test sets. Model performance during and after finishing training was evaluated by loss functions and various indexes, respectively. Based on loss functions, YOLOv5-seg demonstrated a lower error rate in detecting rather than classifying sea turtles than the YOLOv5. According to mean Average Precision (mAP) values, which reflect precision and recall, the YOLOv5-seg model showed superior performance than YOLOv5. The mAP0.5 and mAP0.5:0.95 for the YOLOv5 model were 0.885 and 0.795, respectively, whereas for the YOLOv5-seg, these values were 0.918 and 0.831, respectively. In particular, based on the loss functions and classification results, the YOLOv5-seg showed improved performance for detecting rather than classifying sea turtles compared to the YOLOv5. The results of this study may help improve sea turtle monitoring in the future.

This paper introduces new flexible loss functions for binary classification in Gradient-Boosted Decision Trees (GBDT) that combine Dice-based and cross-entropy-based losses and offer link functions from either a generalized extreme value (GEV) or exponentiated exponential logistic (EEL) distribution. Testing 27 different GBDT models using XGBoost on a Freddie Mac mortgage loan database showed that the choice of the loss function is useful. Specifically, when the class imbalance ratio (IR) is less than 99, using a skewed GEV distribution-based link function in XGBoost enhances discriminatory power and classification accuracy while retaining a simple model structure, which is particularly important in credit scoring applications. In cases where class imbalances are severe, typically between IRs of 99 and 200, we found that an advanced loss function, which is composed of a symmetric hybrid loss function and a link derived from a positively skewed EEL distribution, outperforms other XGBoost variants. Based on our findings, the accuracy improvements of these proposed extensions result in lower misclassification costs, which are especially evident when IR is below 99, which results in higher profitability for the business. Furthermore, the study highlights the transparency associated with GBDT, which is also an integral component of financial applications. Researchers and practitioners can use these insights to create more accurate and discriminative machine learning models, with possible extensions to other GBDT implementations and machine learning techniques that take into account loss functions. The source code for the proposed approach is publicly available at https://github.com/jm-ml/flexible-losses-for-binary-classification-with-GBDT.

Automatic modulation classification (AMC) has a wide range of applications in both civilian and military fields, such as industrial Internet of Things (IIoT) security, communication spectrum management, and military electronic countermeasures. However, label mislabeling often occurs in practical scenarios, significantly impacting the performance and robustness of deep neural networks (DNNs). In this article, we propose a meta-learning guided label noise distillation method to enhance the robustness of AMC models against label noise or errors. Specifically, we propose a teacher-student heterogeneous network (TSHN) to discriminate and distill label noise. Following the notion that labels represent information, a teacher network, utilizing trusted few-shot labeled samples, reevaluates and corrects labels for a considerable number of untrusted labeled samples through meta-learning. By dividing and conquering untrusted labeled samples according to their confidence levels, the student network learns more effectively. Additionally, we propose a multiview signal (MVS) method to further enhance the performance of hard-to-classify categories with few-shot trusted labeled samples. Extensive experiments on the RadioML2016 and HisarMod2019.1 data sets demonstrate that our methods significantly improve accuracy and robustness in signal AMC across diverse label noise scenarios, including symmetric, asymmetric, and mixed label noise. For example, compared to the baseline convolutional neural network with the cross-entropy loss, our proposed TSHN achieves a remarkable 1.26% to 36.84% accuracy improvement under symmetric label noise and 0.12% to 38.59% accuracy improvement under mixed label noise. Moreover, TSHN exhibits greater robustness to varying label noise rates compared to existing methods.

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source, distribution, and the loss function used to train deep neural networks. Currently, the cross-entropy loss remains the de-facto loss function for training deep learning classifiers. This loss function, however, asserts equal learning from all classes, leading to a bias toward the majority class. Although the choice of the loss function impacts model performance, to the best of our knowledge, we observed that no literature exists that performs a comprehensive analysis and selection of an appropriate loss function toward the classification task under study. In this work, we benchmark various state-of-the-art loss functions, critically analyze model performance, and propose improved loss functions for a multi-class classification task. We select a pediatric chest X-ray (CXR) dataset that includes images with no abnormality (normal), and those exhibiting manifestations consistent with bacterial and viral pneumonia. We construct prediction-level and model-level ensembles to improve classification performance. Our results show that compared to the individual models and the state-of-the-art literature, the weighted averaging of the predictions for top-3 and top-5 model-level ensembles delivered significantly superior classification performance (p < 0.05) in terms of MCC (0.9068, 95% confidence interval (0.8839, 0.9297)) metric. Finally, we performed localization studies to interpret model behavior and confirm that the individual models and ensembles learned task-specific features and highlighted disease-specific regions of interest. The code is available at https://github.com/sivaramakrishnan-rajaraman/multiloss_ensemble_models.

Classification task is one of the most common tasks in machine learning. This supervised learning problem consists in assigning each input to one of a finite number of discrete categories. Classification task appears naturally in numerous applications, such as medical image processing, speech recognition, maintenance systems, accident detection, autonomous driving etc.In the last decade methods of deep learning have proven to be extremely efficient in multiple machine learning problems, including classification. Whereas the neural network architecture might depend a lot on data type and restrictions posed by the nature of the problem (for example, real-time applications), the process of its training (i.e. finding model’s parameters) is almost always presented as loss function optimization problem.Cross-entropy is a loss function often used for multiclass classification problems, as it allows to achieve high accuracy results.Here we propose to use a generalized version of this loss based on Renyi divergence and entropy. We remark that in case of binary labels proposed generalization is reduced to cross-entropy, thus we work in the context of soft labels. Specifically, we consider a problem of image classification being solved by application of convolution neural networks with mixup regularizer. The latter expands the training set by taking convex combination of pairs of data samples and corresponding labels. Consequently, labels are no longer binary (corresponding to single class), but have a form of vector of probabilities. In such settings cross-entropy and proposed generalization with Renyi divergence and entropy are distinct, and their comparison makes sense.To measure effectiveness of the proposed loss function we consider image classification problem on benchmark CIFAR-10 dataset. This dataset consists of 60000 images belonging to 10 classes, where images are color and have the size of 32×32. Training set consists of 50000 images, and the test set contains 10000 images.For the convolution neural network, we follow [1] where the same classification task was studied with respect to different loss functions and consider the same neural network architecture in order to obtain comparable results.Experiments demonstrate superiority of the proposed method over cross-entropy for loss function parameter value α &lt; 1. For parameter value α &gt; 1 proposed method shows worse results than cross-entropy loss function. Finally, parameter value α = 1 corresponds to cross-entropy.

Abstract. The deep learning (DL) models require timely updates to continue their reliability and robustness in prediction, classification, and segmentation tasks. When the deep learning models are tested with a limited test set, the model will not reveal the drawbacks. Every deep learning baseline model needs timely updates by incorporating more data, change in architecture, and hyper parameter tuning. This work focuses on updating the Conditional Generative Adversarial Network (C-GAN) based epiphyte identification deep learning model by incorporating 4 different generator architectures of GAN and two different loss functions. The four generator architectures used in this task are Resnet-6. Resnet-9, Resnet-50 and Resnet-101. A new annotation method called background removed annotation was tested to analyse the improvement in the epiphyte identification protocol. All the results obtained from the model by changing the above parameters are reported using two common evaluation metrics. Based on the parameter tuning experiment, Resnet-6, and Resnet- 9, with binary cross-entropy (BCE) as the loss function, attained higher scores also Resnet-6 with MSE as loss function performed well. The new annotation by removing the background had minimal effect on identifying the epiphytes.

Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two directions that shed more light on the top-k error. First, we provide an in-depth analysis of established and recently proposed single-label multiclass methods along with a detailed account of efficient optimization algorithms for them. Our results indicate that the softmax loss and the smooth multiclass SVM are surprisingly competitive in top-k error uniformly across all k, which can be explained by our analysis of multiclass top-k calibration. Further improvements for a specific k are possible with a number of proposed top-k loss functions. Second, we use the top-k methods to explore the transition from multiclass to multilabel learning. In particular, we find that it is possible to obtain effective multilabel classifiers on Pascal VOC using a single label per image for training, while the gap between multiclass and multilabel methods on MS COCO is more significant. Finally, our contribution of efficient algorithms for training with the considered top-k and multilabel loss functions is of independent interest.

Leaves are one of the plant components that play a crucial role in plant productivity. Leaf disease in lemon plants can negatively impact both productivity and plant health. Therefore, a computer-based system for auto-matic classification was developed to efficiently and accurately identify dis-eases in lemon leaves. The automatic disease classification process in lemon leaves plays an important role for farmers, supporting timely and accurate decision-making. This study compared several deep learning and transformer models for disease classification of lemon leaves based on their images. The main objective of this study was to determine the performance of each deep learning and transformer architecture for disease classification in lemon leaves using image-based features. In evaluating various experiments, two deep learning models performed well: InceptionV3 and Xception, with accu-racies of 99.85% and 99.63%, respectively, and minimum loss values of 0.017% and 0.0018%, respectively. Then, the transformer model using the Vision Transformer architecture outperformed the two best deep learning models, achieving 99.89% accuracy and a loss of 0.0013. Overall, the experiment comparing the deep learning model and the transformer shows that the Vision Transformer outperforms the CNN. Consequently, the Vision Trans-former presents strong potential as an effective and robust approach for im-age-based leaf disease detection in lemon plants.

Plant fungal diseases are one of the most important causes of crop yield losses. Therefore, plant disease identification algorithms have been seen as a useful tool to detect them at early stages to mitigate their effects. Although deep-learning based algorithms can achieve high detection accuracies, they require large and manually annotated image datasets that is not always accessible, specially for rare and new diseases. This study focuses on the development of a plant disease detection algorithm and strategy requiring few plant images (Few-shot learning algorithm). We extend previous work by using a novel challenging dataset containing more than 100,000 images. This dataset includes images of leaves, panicles and stems of five different crops (barley, corn, rape seed, rice, and wheat) for a total of 17 different diseases, where each disease is shown at different disease stages. In this study, we propose a deep metric learning based method to extract latent space representations from plant diseases with just few images by means of a Siamese network and triplet loss function. This enhances previous methods that require a support dataset containing a high number of annotated images to perform metric learning and few-shot classification. The proposed method was compared over a traditional network that was trained with the cross-entropy loss function. Exhaustive experiments have been performed for validating and measuring the benefits of metric learning techniques over classical methods. Results show that the features extracted by the metric learning based approach present better discriminative and clustering properties. Davis-Bouldin index and Silhouette score values have shown that triplet loss network improves the clustering properties with respect to the categorical-cross entropy loss. Overall, triplet loss approach improves the DB index value by 22.7% and Silhouette score value by 166.7% compared to the categorical cross-entropy loss model. Moreover, the F-score parameter obtained from the Siamese network with the triplet loss performs better than classical approaches when there are few images for training, obtaining a 6% improvement in the F-score mean value. Siamese networks with triplet loss have improved the ability to learn different plant diseases using few images of each class. These networks based on metric learning techniques improve clustering and classification results over traditional categorical cross-entropy loss networks for plant disease identification.

Multi-label classification of remote sensing (RS) images under the deep learning framework has attracted increasing attentions. However, manual annotation of RS images is time-consuming and easily results in missing labels due to the subjectivity of human perception. The deep learning models could suffer from performance drop because of the incomplete labels of the training set. To address the issue, a deep learning model with label enhancement is proposed for incomplete multi-label classification of RS images. The model consists of a semantic feature extraction (SFE) module, a label correlation learning (LCL) module and a label enhancement (LE) module. Firstly, the semantic features of RS images are extracted by an improved ResNet-101 in the SFE module. Secondly, the global label correlations are learned by a graph convolutional network (GCN) in the LCL module. Subsequently, the labels predicted according to the semantic features are enhanced by the label correlations and local semantics in the LE module. Finally, a weighted combination of the label probability generated by the semantic features and the enhanced one through the LE module is applied in the loss function for classification. The multi-label classification experiments on three public RS image datasets prove the effectiveness of our model.

PurposeTo conduct a head-to-head comparison between deep learning (DL) and radiomics models across institutions for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) and to investigate the model robustness and generalizability through rigorous internal and external validation.MethodsThis retrospective study included 2304 preoperative images of 576 HCC lesions from two centers, with MVI status determined by postoperative histopathology. We developed DL and radiomics models for predicting the presence of MVI using B-mode ultrasound, contrast-enhanced ultrasound (CEUS) at the arterial, portal, and delayed phases, and a combined modality (B + CEUS). For radiomics, we constructed models with enlarged vs. original regions of interest (ROIs). A cross-validation approach was performed by training models on one center’s dataset and validating the other, and vice versa. This allowed assessment of the validity of different ultrasound modalities and the cross-center robustness of the models. The optimal model combined with alpha-fetoprotein (AFP) was also validated. The head-to-head comparison was based on the area under the receiver operating characteristic curve (AUC).ResultsThirteen DL models and 25 radiomics models using different ultrasound modalities were constructed and compared. B + CEUS was the optimal modality for both DL and radiomics models. The DL model achieved AUCs of 0.802–0.818 internally and 0.667–0.688 externally across the two centers, whereas radiomics achieved AUCs of 0.749–0.869 internally and 0.646–0.697 externally. The radiomics models showed overall improvement with enlarged ROIs (P < 0.05 for both CEUS and B + CEUS modalities). The DL models showed good cross-institutional robustness (P > 0.05 for all modalities, 1.6–2.1% differences in AUC for the optimal modality), whereas the radiomics models had relatively limited robustness across the two centers (12% drop-off in AUC for the optimal modality). Adding AFP improved the DL models (P < 0.05 externally) and well maintained the robustness, but did not benefit the radiomics model (P > 0.05).ConclusionCross-institutional validation indicated that DL demonstrated better robustness than radiomics for preoperative MVI prediction in patients with HCC, representing a promising solution to non-standardized ultrasound examination procedures.