Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook
- URL: http://arxiv.org/abs/2312.05391v1
- Date: Fri, 8 Dec 2023 22:06:05 GMT
- Title: Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook
- Authors: Reza Azad, Moein Heidary, Kadir Yilmaz, Michael H\"uttemann, Sanaz
Karimijafarbigloo, Yuli Wu, Anke Schmeink, Dorit Merhof
- Abstract summary: Loss functions are crucial for shaping the development of deep learning-based segmentation algorithms.
We provide a novel taxonomy and review of how these loss functions are customized and leveraged in image segmentation.
We conclude this review by identifying current challenges and unveiling future research opportunities.
- Score: 11.119967679567587
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Semantic image segmentation, the process of classifying each pixel in an
image into a particular class, plays an important role in many visual
understanding systems. As the predominant criterion for evaluating the
performance of statistical models, loss functions are crucial for shaping the
development of deep learning-based segmentation algorithms and improving their
overall performance. To aid researchers in identifying the optimal loss
function for their particular application, this survey provides a comprehensive
and unified review of $25$ loss functions utilized in image segmentation. We
provide a novel taxonomy and thorough review of how these loss functions are
customized and leveraged in image segmentation, with a systematic
categorization emphasizing their significant features and applications.
Furthermore, to evaluate the efficacy of these methods in real-world scenarios,
we propose unbiased evaluations of some distinct and renowned loss functions on
established medical and natural image datasets. We conclude this review by
identifying current challenges and unveiling future research opportunities.
Finally, we have compiled the reviewed studies that have open-source
implementations on our GitHub page.
Related papers
- Visual Context-Aware Person Fall Detection [52.49277799455569]
We present a segmentation pipeline to semi-automatically separate individuals and objects in images.
Background objects such as beds, chairs, or wheelchairs can challenge fall detection systems, leading to false positive alarms.
We demonstrate that object-specific contextual transformations during training effectively mitigate this challenge.
arXiv Detail & Related papers (2024-04-11T19:06:36Z) - Advancements in Content-Based Image Retrieval: A Comprehensive Survey of
Relevance Feedback Techniques [0.0]
Content-based image retrieval (CBIR) systems have emerged as crucial tools in the field of computer vision.
This survey paper presents a comprehensive overview of CBIR, emphasizing its role in object detection and its potential to identify and retrieve visually similar images based on content features.
It elaborates on the semantic gap, which arises from the disparity between low-level features and high-level semantic concepts, and explores approaches to bridge this gap.
arXiv Detail & Related papers (2023-12-13T11:07:32Z) - A survey and taxonomy of loss functions in machine learning [51.35995529962554]
We present a comprehensive overview of the most widely used loss functions across key applications, including regression, classification, generative modeling, ranking, and energy-based modeling.
We introduce 43 distinct loss functions, structured within an intuitive taxonomy that clarifies their theoretical foundations, properties, and optimal application contexts.
arXiv Detail & Related papers (2023-01-13T14:38:24Z) - Unsupervised Part Discovery from Contrastive Reconstruction [90.88501867321573]
The goal of self-supervised visual representation learning is to learn strong, transferable image representations.
We propose an unsupervised approach to object part discovery and segmentation.
Our method yields semantic parts consistent across fine-grained but visually distinct categories.
arXiv Detail & Related papers (2021-11-11T17:59:42Z) - Common Limitations of Image Processing Metrics: A Picture Story [58.83274952067888]
This document focuses on biomedical image analysis problems that can be phrased as image-level classification, semantic segmentation, instance segmentation, or object detection task.
The current version is based on a Delphi process on metrics conducted by an international consortium of image analysis experts from more than 60 institutions worldwide.
arXiv Detail & Related papers (2021-04-12T17:03:42Z) - Adversarial Feature Augmentation and Normalization for Visual
Recognition [109.6834687220478]
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models.
Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings.
We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
arXiv Detail & Related papers (2021-03-22T20:36:34Z) - Understanding Failures of Deep Networks via Robust Feature Extraction [44.204907883776045]
We introduce and study a method aimed at characterizing and explaining failures by identifying visual attributes whose presence or absence results in poor performance.
We leverage the representation of a separate robust model to extract interpretable features and then harness these features to identify failure modes.
arXiv Detail & Related papers (2020-12-03T08:33:29Z) - A Weakly-Supervised Semantic Segmentation Approach based on the Centroid
Loss: Application to Quality Control and Inspection [6.101839518775968]
We propose and assess a new weakly-supervised semantic segmentation approach making use of a novel loss function.
The performance of the approach is evaluated against datasets from two different industry-related case studies.
arXiv Detail & Related papers (2020-10-26T09:08:21Z) - Online Graph Completion: Multivariate Signal Recovery in Computer Vision [29.89364298411089]
We study the "completion" problem defined on graphs, where requests for additional measurements must be made sequentially.
We design the optimization model in the Fourier domain of the graph describing how ideas based on adaptive submodularity provide algorithms that work well in practice.
On a large set of images collected from Imgur, we see promising results on images that are otherwise difficult to categorize.
arXiv Detail & Related papers (2020-08-12T01:34:21Z) - Saliency-driven Class Impressions for Feature Visualization of Deep
Neural Networks [55.11806035788036]
It is advantageous to visualize the features considered to be essential for classification.
Existing visualization methods develop high confidence images consisting of both background and foreground features.
In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
arXiv Detail & Related papers (2020-07-31T06:11:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.