Every Untrue Label is Untrue in its Own Way: Controlling Error Type with the Log Bilinear Loss

04/20/2017
by   Yehezkel S. Resheff, et al.
0

Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss function used in this context is the cross-entropy loss, which reduces to the log loss in the typical case when there is a single correct response label. While this loss is insensitive to the identity of the assigned class in the case of misclassification, in practice it is often the case that some errors may be more detrimental than others. Here we present the bilinear-loss (and related log-bilinear-loss) which differentially penalizes the different wrong assignments of the model. We thoroughly test this method using standard models and benchmark image datasets. As one application, we show the ability of this method to better contain error within the correct super-class, in the hierarchically labeled CIFAR100 dataset, without affecting the overall performance of the classifier.

READ FULL TEXT

page 7

page 8

page 10

research
07/31/2019

Competing Ratio Loss for Discriminative Multi-class Image Classification

The development of deep convolutional neural network architecture is cri...
research
12/30/2021

A Unified DRO View of Multi-class Loss Functions with top-N Consistency

Multi-class classification is one of the most common tasks in machine le...
research
05/18/2021

Label Inference Attacks from Log-loss Scores

Log-loss (also known as cross-entropy loss) metric is ubiquitously used ...
research
10/01/2017

Image Dehazing using Bilinear Composition Loss Function

In this paper, we introduce a bilinear composition loss function to addr...
research
06/05/2019

Learning to Rank for Plausible Plausibility

Researchers illustrate improvements in contextual encoding strategies vi...
research
05/28/2021

DeepMoM: Robust Deep Learning With Median-of-Means

Data used in deep learning is notoriously problematic. For example, data...
research
02/28/2022

Learning Semantic Segmentation from Multiple Datasets with Label Shifts

With increasing applications of semantic segmentation, numerous datasets...

Please sign up or login with your details

Forgot password? Click here to reset