Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization

04/30/2021
by   Yubin Ge, et al.
0

The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk of misclassification which is usually measured by the distance between the prediction and label in a semantic hierarchical tree. In this paper, we propose to incorporate the risk-aware inter-class correlation in a discrete optimal transport (DOT) training framework by configuring its ground distance matrix. The ground distance matrix can be pre-defined following a priori of hierarchical semantic risk. Specifically, we define the tree induced error (TIE) on a hierarchical semantic tree and extend it to its increasing function from the optimization perspective. The semantic similarity in each level of a tree is integrated with the information gain. We achieve promising results on several large scale image classification tasks with a semantic tree structure in a plug and play manner.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2020

Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training

Semantic segmentation (SS) is an important perception manner for self-dr...
research
08/11/2020

Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving

Semantic segmentation is important for many real-world systems, e.g., au...
research
02/17/2018

Bayes-optimal Hierarchical Classification over Asymmetric Tree-Distance Loss

Hierarchical classification is supervised multi-class classification pro...
research
06/26/2019

Hierarchical Optimal Transport for Document Representation

The ability to measure similarity between documents enables intelligent ...
research
04/18/2022

Hierarchical Optimal Transport for Comparing Histopathology Datasets

Scarcity of labeled histopathology data limits the applicability of deep...
research
11/17/2019

Learning with Hierarchical Complement Objective

Label hierarchies widely exist in many vision-related problems, ranging ...
research
04/01/2021

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

There has been increasing interest in building deep hierarchy-aware clas...

Please sign up or login with your details

Forgot password? Click here to reset