Hyperbolic image segmentation
For image segmentation, the current standard is to perform pixel-level optimization and
inference in Euclidean output embedding spaces through linear hyperplanes. In this work …
inference in Euclidean output embedding spaces through linear hyperplanes. In this work …
Triggering failures: Out-of-distribution detection by learning from local adversarial attacks in semantic segmentation
In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic
segmentation. By analyzing the literature, we found that current methods are either accurate …
segmentation. By analyzing the literature, we found that current methods are either accurate …
Plgan: Generative adversarial networks for power-line segmentation in aerial images
Accurate segmentation of power lines in various aerial images is very important for UAV
flight safety. The complex background and very thin structures of power lines, however …
flight safety. The complex background and very thin structures of power lines, however …
Type-I generative adversarial attack
Deep neural networks are vulnerable to adversarial attacks either by examples with
indistinguishable perturbations which produce incorrect predictions, or by examples with …
indistinguishable perturbations which produce incorrect predictions, or by examples with …
Find it if you can: end-to-end adversarial erasing for weakly-supervised semantic segmentation
Semantic segmentation is a task that traditionally requires a large dataset of pixel-level
ground truth labels, which is time-consuming and expensive to obtain. Recent …
ground truth labels, which is time-consuming and expensive to obtain. Recent …
Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
Equipping predicted segmentation with calibrated uncertainty is essential for safety-critical
applications. In this work, we focus on capturing the data-inherent uncertainty (aka aleatoric …
applications. In this work, we focus on capturing the data-inherent uncertainty (aka aleatoric …
Calibrated adversarial refinement for stochastic semantic segmentation
In semantic segmentation tasks, input images can often have more than one plausible
interpretation, thus allowing for multiple valid labels. To capture such ambiguities, recent …
interpretation, thus allowing for multiple valid labels. To capture such ambiguities, recent …
Instance-aware observer network for out-of-distribution object segmentation
Recent works on predictive uncertainty estimation have shown promising results on Out-Of-
Distribution (OOD) detection for semantic segmentation. However, these methods struggle to …
Distribution (OOD) detection for semantic segmentation. However, these methods struggle to …
[PDF][PDF] 基于一种条件熵距离惩罚的生成式对抗网络
谭宏卫， 王国栋， 周林勇， 张自力 - 软件学报, 2020 - jos.org.cn
生成高质量的样本一直是生成式对抗网络(Generative Adversarial Networks, GANs)
领域的主要挑战之一. 鉴于此, 本文利用条件熵构建一种距离, 并将此直接惩罚于GANs …
领域的主要挑战之一. 鉴于此, 本文利用条件熵构建一种距离, 并将此直接惩罚于GANs …
Gambling Adversarial Nets for Hard Sample Mining and Structured Prediction: Application in Ultrasound Thyroid Nodule Segmentation
M Bakhtiariziabari, M Ghafoorian - … , MLMI 2020, Held in Conjunction with …, 2020 - Springer
Most real-world datasets are characterized by long-tail distributions over classes or, more
generally, over underlying visual representations. Consequently, not all samples contribute …
generally, over underlying visual representations. Consequently, not all samples contribute …