English
Related papers

Related papers: Optimized Hybrid Focal Margin Loss for Crack Segme…

200 papers

Imbalanced datasets pose a considerable challenge in training deep learning (DL) models for medical diagnostics, particularly for segmentation tasks. Imbalance may be associated with annotation quality limited annotated datasets, rare…

Image and Video Processing · Electrical Eng. & Systems 2025-04-08 Bashir Alam , Masa Cirkovic , Mete Harun Akcay , Md Kaf Shahrier , Sebastien Lafond , Hergys Rexha , Kurt Benke , Sepinoud Azimi , Janan Arslan

We propose two novel loss functions, Multiplicative Loss and Confidence-Adaptive Multiplicative Loss, for semantic segmentation in medical and cellular images. Although Cross Entropy and Dice Loss are widely used, their additive combination…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Yuto Yokoi , Kazuhiro Hotta

We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Serim Ryou , Seong-Gyun Jeong , Pietro Perona

Tool wear monitoring is crucial for quality control and cost reduction in manufacturing processes, of which drilling applications are one example. In this paper, we present a U-Net based semantic image segmentation pipeline, deployed on…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Elke Schlager , Andreas Windisch , Lukas Hanna , Thomas Klünsner , Elias Jan Hagendorfer , Tamara Teppernegg

Intersection over Union (IoU) losses are surrogates that directly optimize the Jaccard index. Leveraging IoU losses as part of the loss function have demonstrated superior performance in semantic segmentation tasks compared to optimizing…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Zifu Wang , Xuefei Ning , Matthew B. Blaschko

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Tsung-Yi Lin , Priya Goyal , Ross Girshick , Kaiming He , Piotr Dollár

It is important to extract good features using an encoder to realize semantic segmentation with high accuracy. Although loss function is optimized in training deep neural network, far layers from the layers for computing loss function are…

Image and Video Processing · Electrical Eng. & Systems 2021-01-21 Takamasa Ando , Kazuhiro Hotta

Fovea localization is one of the most popular tasks in ophthalmic medical image analysis, where the coordinates of the center point of the macula lutea, i.e. fovea centralis, should be calculated based on color fundus images. In this work,…

Image and Video Processing · Electrical Eng. & Systems 2026-02-23 Yuli Wu , Peter Walter , Dorit Merhof

The key factor in implementing machine learning algorithms in decision-making situations is not only the accuracy of the model but also its confidence level. The confidence level of a model in a classification problem is often given by the…

Machine Learning · Statistics 2024-05-02 Masanari Kimura , Hiroki Naganuma

In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement…

Machine Learning · Computer Science 2021-10-05 David Macêdo , Tsang Ing Ren , Cleber Zanchettin , Adriano L. I. Oliveira , Teresa Ludermir

Large scale image classification models trained on top of popular datasets such as Imagenet have shown to have a distributional skew which leads to disparities in prediction accuracies across different subsections of population…

Computer Vision and Pattern Recognition · Computer Science 2021-07-21 Rohan Mahadev , Anindya Chakravarti

Accurate brain image segmentation, particularly for distinguishing various tissues from magnetic resonance imaging (MRI) images, plays a pivotal role in finding the neurological dis ease and medical image computing. In deep learning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Hanuman Verma , Akshansh Gupta , Pranabesh Maji , Saurav Mandal , Vijay Kumar Pandey

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Kai Yao , Alberto Ortiz , Francisco Bonnin-Pascual

The accuracy of deep learning methods for two foundational tasks in medical image analysis -- detection and segmentation -- can suffer from class imbalance. We propose a `switching loss' function that adaptively shifts the emphasis between…

Image and Video Processing · Electrical Eng. & Systems 2020-08-11 Deepak Anand , Gaurav Patel , Yaman Dang , Amit Sethi

Learning discriminative deep feature embeddings by using million-scale in-the-wild datasets and margin-based softmax loss is the current state-of-the-art approach for face recognition. However, the memory and computing cost of the Fully…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Xiang An , Jiankang Deng , Jia Guo , Ziyong Feng , Xuhan Zhu , Jing Yang , Tongliang Liu

Medical image segmentation has played an important role in medical analysis and widely developed for many clinical applications. Deep learning-based approaches have achieved high performance in semantic segmentation but they are limited to…

Image and Video Processing · Electrical Eng. & Systems 2020-12-07 Ngan Le , Trung Le , Kashu Yamazaki , Toan Duc Bui , Khoa Luu , Marios Savides

In this paper, we propose a fuzzy adaptive loss function for enhancing deep learning performance in classification tasks. Specifically, we redefine the cross-entropy loss to effectively address class-level noise conditions, including the…

Machine Learning · Computer Science 2023-10-13 Sebastián Maldonado , Carla Vairetti , Katherine Jara , Miguel Carrasco , Julio López

The top-k error is a common measure of performance in machine learning and computer vision. In practice, top-k classification is typically performed with deep neural networks trained with the cross-entropy loss. Theoretical results indeed…

Machine Learning · Computer Science 2018-02-22 Leonard Berrada , Andrew Zisserman , M. Pawan Kumar

The task of roof damage classification and segmentation from overhead imagery presents unique challenges. In this work we choose to address the challenge posed due to strong class imbalance. We propose four distinct techniques that aim at…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Jean-Baptiste Boin , Nat Roth , Jigar Doshi , Pablo Llueca , Nicolas Borensztein

A deep convolutional neural network (CNN) has been widely used in image classification and gives better classification accuracy than the other techniques. The softmax cross-entropy loss function is often used for classification tasks. There…

Computer Vision and Pattern Recognition · Computer Science 2020-04-20 Motoshi Abe , Junichi Miyao , Takio Kurita