Multi-level OOD detection in image segmentation networks for safety in automotive applications
This research paper aims to study the efficacy of utilizing multi-layer outputs from semantic segmentation models for handling various types of out-of-distribution (OOD) samples. Specifically, our focus lies on the comparison between early and late layers to determine which layer proves more e...
Main Author: | Poh, Eugene Yang Quan |
---|---|
Other Authors: | Arvind Easwaran |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/175033 |
Similar Items
-
Out-of-Distribution (OOD) Detection and Generalization Improved by Augmenting Adversarial Mixup Samples
by: Kyungpil Gwon, et al.
Published: (2023-03-01) -
Bridge Pre-Training and Clustering: A Unified Contrastive Learning Framework for OOD Intent Discovery
by: Yutao Mou, et al.
Published: (2023-01-01) -
Improvement in automatic food region extraction based on saliency detection
by: Takuya Futagami, et al.
Published: (2022-12-01) -
Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding
by: Niraj Kumar, et al.
Published: (2021-01-01) -
AdvSCOD: Bayesian-Based Out-Of-Distribution Detection via Curvature Sketching and Adversarial Sample Enrichment
by: Jiacheng Qiao, et al.
Published: (2023-01-01)