Making Better Mistakes: Leveraging Class Hierarchies With Deep Networks
| Autor: | Nicholas A. Lord, Luca Bertinetto, Sina Samangooei, Romain Mueller, Konstantinos Tertikas |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Contextual image classification Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Data science Graph Machine Learning (cs.LG) Visualization 0202 electrical engineering electronic engineering information engineering Graph (abstract data type) 020201 artificial intelligence & image processing Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr42600.2020.01252 |
| Popis: | Deep neural networks have improved image classification dramatically over the past decade, but have done so by focusing on performance measures that treat all classes other than the ground truth as equally wrong. This has led to a situation in which mistakes are less likely to be made than before, but are equally likely to be absurd or catastrophic when they do occur. Past works have recognised and tried to address this issue of mistake severity, often by using graph distances in class hierarchies, but this has largely been neglected since the advent of the current deep learning era in computer vision. In this paper, we aim to renew interest in this problem by reviewing past approaches and proposing two simple modifications of the cross-entropy loss which outperform the prior art under several metrics on two large datasets with complex class hierarchies: tieredImageNet and iNaturalist'19. To appear at CVPR 2020. Code available at https://github.com/fiveai/making-better-mistakes |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|