English
Related papers

Related papers: Boundary and Entropy-driven Adversarial Learning f…

200 papers

The Segment Anything Model (SAM) has gained popularity as a versatile image segmentation method, thanks to its strong generalization capabilities across various domains. However, when applied to optic disc (OD) and optic cup (OC)…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Jinchen Yu , Yongwei Nie , Fei Qi , Wenxiong Liao , Hongmin Cai

The development of artificial intelligence models for macular edema (ME) analy-sis always relies on expert-annotated pixel-level image datasets which are expen-sive to collect prospectively. While anomaly-detection-based weakly-supervised…

Image and Video Processing · Electrical Eng. & Systems 2025-08-27 Yuhui Tao , Yizhe Zhang , Qiang Chen

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Subeesh Vasu , Mateusz Kozinski , Leonardo Citraro , Pascal Fua

Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy and Bayesian, often rely on an…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Siteng Ma , Haochang Wu , Aonghus Lawlor , Ruihai Dong

The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Hye-Seong Hong , Abhishek Kumar , Dong-Gyu Lee

A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…

Computer Vision and Pattern Recognition · Computer Science 2022-01-05 Runqi Wang , Xiaoyue Duan , Baochang Zhang , Song Xue , Wentao Zhu , David Doermann , Guodong Guo

Automated optic disc (OD) and optic cup (OC) segmentation in fundus images is relevant to efficiently measure the vertical cup-to-disc ratio (vCDR), a biomarker commonly used in ophthalmology to determine the degree of glaucomatous optic…

Unsupervised domain adaptation (UDA) between two significantly disparate domains to learn high-level semantic alignment is a crucial yet challenging task.~To this end, in this work, we propose exploiting low-level edge information to…

Computer Vision and Pattern Recognition · Computer Science 2022-01-14 Xiaofeng Liu , Fangxu Xing , Georges El Fakhri , Jonghye Woo

Significant advances have been made towards building accurate automatic segmentation systems for a variety of biomedical applications using machine learning. However, the performance of these systems often degrades when they are applied on…

Federated learning (FL) is a trending training paradigm to utilize decentralized training data. FL allows clients to update model parameters locally for several epochs, then share them to a global model for aggregation. This training…

Machine Learning · Computer Science 2022-08-09 Xiaoxiao Li , Zhao Song , Jiaming Yang

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…

Machine Learning · Computer Science 2020-04-14 Haidong Xie , Xueshuang Xiang , Naijin Liu , Bin Dong

Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in the presence of limited amount of labeled data. In this…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Avisek Lahiri , Vineet Jain , Arnab Mondal , Prabir Kumar Biswas

One of the important parameters for the assessment of glaucoma is optic nerve head (ONH) evaluation, which usually involves depth estimation and subsequent optic disc and cup boundary extraction. Depth is usually obtained explicitly from…

Image and Video Processing · Electrical Eng. & Systems 2020-07-16 Sharath M Shankaranarayana , Keerthi Ram , Kaushik Mitra , Mohanasankar Sivaprakasam

This paper introduces a divide-and-conquer inspired adversarial learning (DACAL) approach for photo enhancement. The key idea is to decompose the photo enhancement process into hierarchically multiple sub-problems, which can be better…

Image and Video Processing · Electrical Eng. & Systems 2019-10-24 Zhiwu Huang , Danda Pani Paudel , Guanju Li , Jiqing Wu , Radu Timofte , Luc Van Gool

Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain. Existing domain adversarial learning methods are not suitable for OSDA because distribution matching with…

Machine Learning · Computer Science 2022-10-25 JoonHo Jang , Byeonghu Na , DongHyeok Shin , Mingi Ji , Kyungwoo Song , Il-Chul Moon

We present a neural point cloud rendering pipeline through a novel multi-frequency-aware patch adversarial learning framework. The proposed approach aims to improve the rendering realness by minimizing the spectrum discrepancy between real…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Jay Karhade , Haiyue Zhu , Ka-Shing Chung , Rajesh Tripathy , Wei Lin , Marcelo H. Ang

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the…

Computer Vision and Pattern Recognition · Computer Science 2025-01-06 Yufei Song , Ziqi Zhou , Minghui Li , Xianlong Wang , Hangtao Zhang , Menghao Deng , Wei Wan , Shengshan Hu , Leo Yu Zhang

Multi-class semantic segmentation remains a cornerstone challenge in computer vision. Yet, dataset creation remains excessively demanding in time and effort, especially for specialized domains. Active Learning (AL) mitigates this challenge…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Fei Wu , Pablo Marquez-Neila , Hedyeh Rafi-Tarii , Raphael Sznitman

Fundus photography is the primary method for retinal imaging and essential for diabetic retinopathy prevention. Automated segmentation of fundus photographs would improve the quality, capacity, and cost-effectiveness of eye care screening…

Image and Video Processing · Electrical Eng. & Systems 2021-08-29 Jan Kukačka , Anja Zenz , Marcel Kollovieh , Dominik Jüstel , Vasilis Ntziachristos

Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large scale screening is the inability to exhaustively detect fine blood…

Machine Learning · Computer Science 2016-03-16 Debapriya Maji , Anirban Santara , Pabitra Mitra , Debdoot Sheet