English
Related papers

Related papers: Perceptual impact of the loss function on deep-lea…

200 papers

Margin-based losses, especially one-class classification loss, have improved the generalization capabilities of countermeasure systems (CMs), but their reliability is not tested with spoofing attacks degraded with channel variation. Our…

Machine Learning · Computer Science 2022-06-28 Rohit Arora , Anmol Arora , Rohit Singh Rathore

Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing, e.g., in distributed applications, coding methods must…

Image and Video Processing · Electrical Eng. & Systems 2025-08-27 Samuel Fernández-Menduiña , Eduardo Pavez , Antonio Ortega

This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems. We consider seven loss functions: 1) cross-entropy loss; 2) focal loss; 3)…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Hichame Yessou , Gencer Sumbul , Begüm Demir

Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Sudeep Katakol , Basem Elbarashy , Luis Herranz , Joost van de Weijer , Antonio M. Lopez

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source,…

Image and Video Processing · Electrical Eng. & Systems 2021-11-16 Sivaramakrishnan Rajaraman , Ghada Zamzmi , Sameer Antani

Deep learning (DL) shows promise of advantages over conventional signal processing techniques in a variety of imaging applications. The networks' being trained from examples of data rather than explicitly designed allows them to learn…

Image and Video Processing · Electrical Eng. & Systems 2023-09-27 Obaidullah Rahman , Ken D. Sauer , Madhuri Nagare , Charles A. Bouman , Roman Melnyk , Jie Tang , Brian Nett

The objective of most Reinforcement Learning painting agents is to minimize the loss between a target image and the paint canvas. Human painter artistry emphasizes important features of the target image rather than simply reproducing it…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Peter Schaldenbrand , Jean Oh

Perception-aware lossy source coding has attracted significant recent interest. It augments the classical distortion criterion with an explicit perception constraint, thereby enabling more refined control over fidelity and perceptual…

Information Theory · Computer Science 2026-04-22 Ali Hussein , Jun Chen , Chao Tian , S. Sandeep Pradhan

Recent advances in deep learning, particularly neural networks, have significantly impacted a wide range of fields, including the automatic enhancement of underwater images. This paper presents a deep learning-based approach to improving…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Jose M. Montero , Jose-Luis Lisani

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

Image and Video Processing · Electrical Eng. & Systems 2024-10-21 Daniel Wolf , Tristan Payer , Catharina Silvia Lisson , Christoph Gerhard Lisson , Meinrad Beer , Michael Götz , Timo Ropinski

Especially in lossless image coding the obtainable compression ratio strongly depends on the amount of noise included in the data as all noise has to be coded, too. Different approaches exist for lossless image coding. We analyze the…

Image and Video Processing · Electrical Eng. & Systems 2023-01-12 Wolfgang Schnurrer , Jürgen Seiler , Michael Schöberl , André Kaup

Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Yunfeng Zhao , Huiyu Zhou , Fei Wu , Xifeng Wu

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

Machine Learning · Computer Science 2022-03-01 Tao Huang , Zekang Li , Hua Lu , Yong Shan , Shusheng Yang , Yang Feng , Fei Wang , Shan You , Chang Xu

Representation learning has been increasing its impact on the research and practice of machine learning, since it enables to learn representations that can apply to various downstream tasks efficiently. However, recent works pay little…

Image captioning is a research area of immense importance, aiming to generate natural language descriptions for visual content in the form of still images. The advent of deep learning and more recently vision-language pre-training…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Taraneh Ghandi , Hamidreza Pourreza , Hamidreza Mahyar

Learned Compression (LC) is the emerging technology for compressing image and video content, using deep neural networks. Despite being new, LC methods have already gained a compression efficiency comparable to state-of-the-art image…

Multimedia · Computer Science 2023-05-11 Farhad Pakdaman , Moncef Gabbouj

Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To address this problem, we propose a Channel Importance-driven…

Image and Video Processing · Electrical Eng. & Systems 2026-04-08 Yun Zhang , Junle Liu , Huan Zhang , Zhaoqing Pan , Gangyi Jiang , Weisi Lin

Recent state-of-the-art image segmentation algorithms are mostly based on deep neural networks, thanks to their high performance and fast computation time. However, these methods are usually trained in a supervised manner, which requires…

Computer Vision and Pattern Recognition · Computer Science 2020-01-08 Boah Kim , Jong Chul Ye

The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…

Computer Vision and Pattern Recognition · Computer Science 2015-06-18 Sakrapee Paisitkriangkrai , Chunhua Shen , Anton van den Hengel

Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these simple norms are…

Image and Video Processing · Electrical Eng. & Systems 2020-07-13 Li-Heng Chen , Christos G. Bampis , Zhi Li , Andrey Norkin , Alan C. Bovik