Class-Similarity Based Label Smoothing for Generalized Confidence Calibration

06/24/2020
by   Chihuang Liu, et al.
0

Since modern neural networks are known to be overconfident, several techniques have been recently introduced to address this problem and improve calibration. However, the current notion of calibration is overly simple since only single prediction confidence is considered while the information regarding the rest of the classes is ignored. The output of a neural network is a probability distribution where the scores are estimated confidences of the input belonging to the corresponding classes, and hence they represent a complete estimate of the output likelihood that should be calibrated. In this paper, we first introduce a generalized definition of confidence calibration, which motivates the development of a novel form of label smoothing where the value of each class label is based on its similarity with the reference class. We adopt different similarity measurements, including those that capture semantic similarity, and demonstrate through extensive experiments the advantage of our method over both uniform label smoothing and other techniques.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/11/2021

Instance-based Label Smoothing For Better Calibrated Classification Networks

Label smoothing is widely used in deep neural networks for multi-class c...
research
08/23/2023

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

We address the problem of network calibration adjusting miscalibrated co...
research
12/12/2020

Normalized Label Distribution: Towards Learning Calibrated, Adaptable and Efficient Activation Maps

The vulnerability of models to data aberrations and adversarial attacks ...
research
03/13/2023

Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model

Despite the success of deep neural network (DNN) on sequential data (i.e...
research
09/20/2018

Spline-Based Probability Calibration

In many classification problems it is desirable to output well-calibrate...
research
04/12/2021

Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations

The task of image segmentation is inherently noisy due to ambiguities re...
research
07/18/2021

Top-label calibration

We study the problem of post-hoc calibration for multiclass classificati...

Please sign up or login with your details

Forgot password? Click here to reset