Intra-Class Mixup for Out-of-Distribution Detection
Deep neural networks (DNNs) have found widespread adoption in solving image recognition and natural language processing tasks. However, they make confident mispredictions when presented with data that does not belong to the training distribution, i.e. out-of-distribution (OoD) samples. Research has...
Main Authors: | Deepak Ravikumar, Sangamesh Kodge, Isha Garg, Kaushik Roy |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10064300/ |
Similar Items
-
GBMix: Enhancing Fairness by Group-Balanced Mixup
by: Sangwoo Hong, et al.
Published: (2024-01-01) -
Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement
by: Shuting Wan, et al.
Published: (2023-03-01) -
Mixup Based Cross-Consistency Training for Named Entity Recognition
by: Geonsik Youn, et al.
Published: (2022-11-01) -
MixER: Mixup-Based Experience Replay for Online Class-Incremental Learning
by: Won-Seon Lim, et al.
Published: (2024-01-01) -
Multi-sample $$\zeta $$ ζ -mixup: richer, more realistic synthetic samples from a p-series interpolant
by: Kumar Abhishek, et al.
Published: (2024-03-01)