Trustworthy Long-Tailed Classification
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6960-6969
Abstract
Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and accordingly unpromising performance es-pecially on tail classes. Recently, the ensembling based methods achieve the state-of-the-art performance and show great potential. However, there are two limitations for cur-rent methods. First, their predictions are not trustworthy for failure-sensitive applications. This is especially harmful for the tail classes where the wrong predictions is basically fre-quent. Second, they assign unified numbers of experts to all samples, which is redundant for easy samples with excessive computational cost. To address these issues, we propose a Trustworthy Long-tailed Classification (TLC) method to jointly conduct classification and uncertainty estimation to identify hard samples in a multi-expert framework. Our TLC obtains the evidence-based uncertainty (EvU) and ev-idence for each expert, and then combines these uncer-tainties and evidences under the Dempster-Shafer Evidence Theory (DST). Moreover, we propose a dynamic expert en-gagement to reduce the number of engaged experts for easy samples and achieve efficiency while maintaining promising performances. Finally, we conduct comprehensive ex-periments on the tasks of classification, tail detection, OOD detection and failure prediction. The experimental results show that the proposed TLC outperforms existing methods and is trustworthy with reliable uncertainty.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61976151,61732011)
- National Key Research and Development Program of China (2019YFB2101900)
- A*Star (C211118012)
This publication has 25 references indexed in Scilit:
- Focal Loss for Dense Object Detection2017
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Selection properties of type II maximum likelihood (empirical Bayes) in linear models with individual variance components for predictorsPattern Recognition Letters, 2012
- Learning from Imbalanced DataIEEE Transactions on Knowledge and Data Engineering, 2009
- ImageNet: A large-scale hierarchical image database2009
- Confidence estimation for machine translation2004
- The Pareto, Zipf and other power lawsEconomics Letters, 2001
- A review of robotics in surgeryProceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 2000
- Analyzing a Portion of the ROC CurveMedical Decision Making, 1989
- Upper and Lower Probabilities Induced by a Multivalued MappingThe Annals of Mathematical Statistics, 1967