SemSegLoss: A python package of loss functions for semantic segmentation

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 recent years, various research papers proposed different loss functions used in case of biased data, sparse segmentation, and unbalanced dataset. In this paper, we introduce SemSegLoss, a python package consisting of some of the well-known loss functions widely used for image segmentation. It is developed with the intent to help researchers in the development of novel loss functions and perform an extensive set of experiments on model architectures for various applications. The ease-of-use and flexibility of the presented package have allowed reducing the development time and increased evaluation strategies of machine learning models for semantic segmentation. Furthermore, different applications that use image segmentation can use SemSegLoss because of the generality of its functions. This wide range of applications will lead to the development and growth of AI across all industries.

8 pages, 2 tables

References in corpus (6)

• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling
• Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification
• A comparative study of 2D image segmentation algorithms for traumatic brain lesions using CT data from the ProTECTIII multicenter clinical trial
• Correlation Maximized Structural Similarity Loss for Semantic Segmentation
• Deep learning-based framework for cardiac function assessment in embryonic zebrafish from heart beating videos