Robust Object Detection Against Multi-Type Corruption Without Catastrophic Forgetting During Adversarial Training Under Harsh Autonomous-Driving Environments
It is important to build robust object detector (ROD) in real-world applications because snow, rain, fog, motion blur, and various kinds of corruption can occur in autonomous-driving environments. Adversarial training (AT) is one of the best solutions to build a robust deep neural network. However,...
Main Authors: | Youngjun Kim, Jitae Shin |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10075553/ |
Similar Items
-
Remembering for the right reasons: Explanations reduce catastrophic forgetting
by: Sayna Ebrahimi, et al.
Published: (2021-12-01) -
Mitigating Catastrophic Forgetting with Complementary Layered Learning
by: Sean Mondesire, et al.
Published: (2023-01-01) -
Can sleep protect memories from catastrophic forgetting?
by: Oscar C González, et al.
Published: (2020-08-01) -
ZeroGrad: Costless conscious remedies for catastrophic overfitting in the FGSM adversarial training
by: Zeinab Golgooni, et al.
Published: (2023-09-01) -
Catastrophic Forgetting in Deep Graph Networks: A Graph Classification Benchmark
by: Antonio Carta, et al.
Published: (2022-02-01)