Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data
Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction sinc...
Main Authors: | Matej Grcić, Petra Bevandić, Zoran Kalafatić, Siniša Šegvić |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/24/4/1248 |
Similar Items
-
Dense Semantic Forecasting with Multi-Level Feature Warping
by: Iva Sović, et al.
Published: (2022-12-01) -
Simple Scalable Multimodal Semantic Segmentation Model
by: Yuchang Zhu, et al.
Published: (2024-01-01) -
Revisiting Consistency for Semi-Supervised Semantic Segmentation
by: Ivan Grubišić, et al.
Published: (2023-01-01) -
Dense context distillation network for semantic parsing of oblique UAV images
by: Youli Ding, et al.
Published: (2022-11-01) -
CRFNet: Context ReFinement Network used for semantic segmentation
by: Taeghyun An, et al.
Published: (2023-10-01)