A survey of loss functions for semantic segmentation

Jadon, Shruti

doi:10.1109/cibcb48159.2020.9277638

Cited by 725 publications

(411 citation statements)

References 15 publications

Supporting

Mentioning

405

Contrasting

Unclassified

Order By: Relevance

“…The training parameters are further explained in Table 4 . The calculation for IoU, accuracy, and BF-score measures are given in Equations ( 3 )–( 5 ) [ 48 ].

…”

Section: Resultsmentioning

confidence: 99%

Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion

et al. 2021

View full text Add to dashboard Cite

Breast cancer is becoming more dangerous by the day. The death rate in developing countries is rapidly increasing. As a result, early detection of breast cancer is critical, leading to a lower death rate. Several researchers have worked on breast cancer segmentation and classification using various imaging modalities. The ultrasonic imaging modality is one of the most cost-effective imaging techniques, with a higher sensitivity for diagnosis. The proposed study segments ultrasonic breast lesion images using a Dilated Semantic Segmentation Network (Di-CNN) combined with a morphological erosion operation. For feature extraction, we used the deep neural network DenseNet201 with transfer learning. We propose a 24-layer CNN that uses transfer learning-based feature extraction to further validate and ensure the enriched features with target intensity. To classify the nodules, the feature vectors obtained from DenseNet201 and the 24-layer CNN were fused using parallel fusion. The proposed methods were evaluated using a 10-fold cross-validation on various vector combinations. The accuracy of CNN-activated feature vectors and DenseNet201-activated feature vectors combined with the Support Vector Machine (SVM) classifier was 90.11 percent and 98.45 percent, respectively. With 98.9 percent accuracy, the fused version of the feature vector with SVM outperformed other algorithms. When compared to recent algorithms, the proposed algorithm achieves a better breast cancer diagnosis rate.

show abstract

“…The training parameters are further explained in Table 4 . The calculation for IoU, accuracy, and BF-score measures are given in Equations ( 3 )–( 5 ) [ 48 ].

…”

Section: Resultsmentioning

confidence: 99%

Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion

et al. 2021

View full text Add to dashboard Cite

show abstract

“…All biases and weights in the data reduction layers are initialized to zero, whereas the biases and convolution weights are initialized by sampling from

, where

is the range,

is the number of input channels and a is the kernel size. During training, ADAM optimization is used on the average of the binary cross entropy loss and the dice loss [ 55 , 56 ] between the data and the predictions. The network is implemented using PyTorch [ 57 , 58 ] and is trained on one GeForce GTX TITAN X GPU core with CUDA version 10.1.243.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Task-Driven Learned Hyperspectral Data Reduction Using End-to-End Supervised Deep Learning

et al. 2020

View full text Add to dashboard Cite

An important challenge in hyperspectral imaging tasks is to cope with the large number of spectral bins. Common spectral data reduction methods do not take prior knowledge about the task into account. Consequently, sparsely occurring features that may be essential for the imaging task may not be preserved in the data reduction step. Convolutional neural network (CNN) approaches are capable of learning the specific features relevant to the particular imaging task, but applying them directly to the spectral input data is constrained by the computational efficiency. We propose a novel supervised deep learning approach for combining data reduction and image analysis in an end-to-end architecture. In our approach, the neural network component that performs the reduction is trained such that image features most relevant for the task are preserved in the reduction step. Results for two convolutional neural network architectures and two types of generated datasets show that the proposed Data Reduction CNN (DRCNN) approach can produce more accurate results than existing popular data reduction methods, and can be used in a wide range of problem settings. The integration of knowledge about the task allows for more image compression and higher accuracies compared to standard data reduction methods.

show abstract

“…Tversky Loss gives FN(false negtive) and FP(false positive) different weights to make loss pay more attention to FN rather than equal attention to FN and FP. Log-Cosh Dice Loss [23] is also a variant of Dice Loss by adding Log-Cosh to smooth the loss fuction curve. Generalized Dice Loss [30] integrates multiple categories of Dice Loss and uses one index as the quantitative index of segmentation results.…”

Section: B Region-based Lossmentioning

confidence: 99%

“…A good loss function can greatly improve the segmentation accuracy. At present, the loss function of image semantic segmentation can be roughly divided into four categories [23].…”

Section: ⅰ Introductionmentioning

confidence: 99%

NeighborLoss: A Loss Function Considering Spatial Correlation for Semantic Segmentation of Remote Sensing Image

Yuan

2021

IEEE Access

View full text Add to dashboard Cite

House segmentation of remote sensing image based on deep learning has become the main segmentation method because it can automatically extract features. However, the accuracy of image segmentation is affected not only by the network model, but also by the loss function, but the existing loss functions, except Binary Cross Entropy, are designed to deal with imbalanced dataset, no new research on improving Binary Cross Entropy for balanced dataset, and all loss function treat each pixel in isolation, without considering the spatial correlation between pixel and its neighbor pixels. To solve this problem, a new loss function, named NeighborLoss function, is proposed. Firstly, the deep learning network is used to get the prediction results of each pixel. According to whether the prediction results of the eight neighboring pixels of each pixel are consistent with the each pixel prediction, different weights are given to each pixel. Finally, the weighted average value of cross entropy of all pixels in the batch is taken as the final loss function value. We use the main deep learning semantic segmentation networks SegNet, PSPNet, UNET + +, MUNet with both NeighborLoss and cross entropy loss respectively to extract houses on the open data set named WHU dataset for remote sensing. The results show that compared with cross entropy loss functions, the MIoU, Precision, Recall, and Accuracy of NeighborLoss function are improved. From the predicted graph, the NeighborLoss function is more accurate to extract the edge of the house, especially in the corner of the house. NeighborLoss function is a more effective loss function for remote sensing image segmentation.

show abstract

A survey of loss functions for semantic segmentation

Cited by 725 publications

References 15 publications

Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion

Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion

Task-Driven Learned Hyperspectral Data Reduction Using End-to-End Supervised Deep Learning

NeighborLoss: A Loss Function Considering Spatial Correlation for Semantic Segmentation of Remote Sensing Image

Contact Info

Product

Resources

About