Improving Entropic Out-of-Distribution Detection using Isometric Distances and the Minimum Distance Score

05/30/2021
by   David Macêdo, et al.
0

Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all the previously mentioned drawbacks). The entropic out-of-distribution detection solution comprises the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a SoftMax loss drop-in replacement because swapping the SoftMax loss with the IsoMax loss requires no changes in the model's architecture or training procedures/hyperparameters. In this paper, we propose to perform what we call an isometrization of the distances used in the IsoMax loss. Additionally, we propose to replace the entropic score with the minimum distance score. Our experiments showed that these simple modifications increase out-of-distribution detection performance while keeping the solution seamless. Code available at $\href{https://github.com/dlmacedo/entropic-out-of-distribution-detection}{\text{entropic out-of-distribution detection}}$.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2022

Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning

Detecting Out-of-Domain (OOD) or unknown intents from user queries is es...
research
01/18/2022

Adversarial vulnerability of powerful near out-of-distribution detection

There has been a significant progress in detecting out-of-distribution (...
research
08/17/2021

Exploring Classification Equilibrium in Long-Tailed Object Detection

The conventional detectors tend to make imbalanced classification and su...
research
12/15/2022

NBC-Softmax : Darkweb Author fingerprinting and migration tracking

Metric learning aims to learn distances from the data, which enhances th...

Please sign up or login with your details

Forgot password? Click here to reset