A survey of loss functions for semantic segmentation
Shruti Jadon
- pp 1-7
Reads0
Chats0
TLDR
A new log-cosh dice loss function is introduced and it is showcased that certain loss functions perform well across all data-sets and can be taken as a good baseline choice in unknown data distribution scenarios.Abstract:
Image Segmentation has been an active field of research as it has a wide range of applications, ranging from automated disease detection to self driving cars. In the past five years, various papers came up with different objective loss functions used in different cases such as biased data, sparse segmentation, etc. In this paper, we have summarized some of the well-known loss functions widely used for Image Segmentation and listed out the cases where their usage can help in fast and better convergence of a model. Furthermore, we have also introduced a new log-cosh dice loss function and compared its performance on NBFS skull-segmentation open source data-set with widely used loss functions. We also showcased that certain loss functions perform well across all data-sets and can be taken as a good baseline choice in unknown data distribution scenarios.read more
Citations
More filters
Posted Content
Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation
TL;DR: In this paper, the authors proposed a Unified Focal loss, a new framework that generalizes Dice and cross entropy-based losses for handling class imbalance, and evaluated their proposed loss function on three highly class imbalanced, publicly available medical imaging datasets.
Journal ArticleDOI
Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation
TL;DR: In this article , the Unified Focal Loss (UFL) is proposed to handle class imbalance in medical image segmentation. But the proposed loss function is not robust to class imbalance and consistently outperforms the other loss functions.
Journal ArticleDOI
D-former: a U-shaped Dilated Transformer for 3D medical image segmentation
TL;DR: In this article , the authors proposed a new method called Dilated Transformer, which conducts self-attention alternately in local and global scopes for pair-wise patch relations capturing.
Journal ArticleDOI
An attention-based U-Net for detecting deforestation within satellite sensor imagery
TL;DR: In this paper , an Attention U-Net deep network for semantic segmentation using Sentinel-2 satellite sensor imagery, for the purpose of detecting deforestation within two forest biomes in South America, the Amazon Rainforest and the Atlantic Forest, was proposed.
Journal ArticleDOI
An overview of deep learning in medical imaging
TL;DR: In this paper, an overview of current deep learning methods, starting from the most straightforward concept but accompanied by the mathematical models that are behind the functionality of this type of intelligence, is presented.
References
More filters
Proceedings ArticleDOI
Focal Loss for Dense Object Detection
TL;DR: This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Proceedings ArticleDOI
Holistically-Nested Edge Detection
Saining Xie,Zhuowen Tu +1 more
TL;DR: HED turns pixel-wise edge classification into image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets to approach the human ability to resolve the challenging ambiguity in edge and object boundary detection.
Book ChapterDOI
Tversky loss function for image segmentation using 3D fully convolutional deep networks
TL;DR: A generalized loss function based on the Tversky index is proposed to address the issue of data imbalance and achieve much better trade-off between precision and recall in training 3D fully convolutional deep neural networks.
Proceedings ArticleDOI
A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation
TL;DR: In this article, a generalized focal loss function based on the Tversky index was proposed to address the issue of data imbalance in medical image segmentation, which achieved a better trade off between precision and recall when training on small structures such as lesions.
Proceedings ArticleDOI
The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
TL;DR: In this article, a method for direct optimization of the mean intersection-over-union loss in neural networks, based on the convex LovAisz extension of submodular losses, is presented.