Raising the bar on the evaluation of out-of-distribution detection
In image classification, a lot of development has happened in detecting out-of-distribution (OoD) data. However, most OoD detection methods are evaluated on a standard set of datasets, arbitrarily different from training data. There is no clear definition of what forms a "good" OoD dataset...
Những tác giả chính: | Mukhoti, J, Lin, T-Y, Chen, B-C, Shah, A, Torr, PHS, Dokania, PK, Lim, S-N |
---|---|
Định dạng: | Conference item |
Ngôn ngữ: | English |
Được phát hành: |
EEE
2023
|
Những quyển sách tương tự
-
Using mixup as a regularizer can surprisingly improve accuracy and out-of-distribution robustness
Bằng: Pinto, F, et al.
Được phát hành: (2023) -
Placing objects in context via inpainting for out-of-distribution segmentation
Bằng: De Jorge, P, et al.
Được phát hành: (2024) -
On using focal loss for neural network calibration
Bằng: Mukhoti, J, et al.
Được phát hành: (2020) -
Calibrating deep neural networks using focal loss
Bằng: Mukhoti, J, et al.
Được phát hành: (2020) -
GDumb: A simple approach that questions our progress in continual learning
Bằng: Prabhu, A, et al.
Được phát hành: (2020)