Research on the robustness of the open-world test-time training model
IntroductionGeneralizing deep learning models to unseen target domains with low latency has motivated research into test-time training/adaptation (TTT/TTA). However, deploying TTT/TTA in open-world environments is challenging due to the difficulty in distinguishing between strong out-of-distribution...
Saved in:
| Main Authors: | Shu Pi, Xin Wang, Jiatian Pi |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2025.1621025/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
On Adversarial Robust Generalization of DNNs for Remote Sensing Image Classification
by: Wei Xue, et al.
Published: (2025-01-01) -
High-robustness integrated adversarial training method for fingerprint-based indoor localization systems
by: ZHANG Xuejun, et al.
Published: (2025-01-01) -
A Backdoor Approach With Inverted Labels Using Dirty Label-Flipping Attacks
by: Orson Mengara
Published: (2025-01-01) -
Evaluating Adversarial Robustness of No-Reference Image and Video Quality Assessment Models with Frequency-Masked Gradient Orthogonalization Adversarial Attack
by: Khaled Abud, et al.
Published: (2025-06-01) -
Triple Down on Robustness: Understanding the Impact of Adversarial Triplet Compositions on Adversarial Robustness
by: Sander Joos, et al.
Published: (2025-02-01)