CISPA
Browse

Long-Tailed Recognition Using Class-Balanced Experts

Download (4.86 MB)
conference contribution
posted on 2023-11-29, 18:15 authored by Saurabh Sharma, Ning Yu, Mario FritzMario Fritz, Bernt Schiele
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance amongst the classes and data scarcity for mediumshot or fewshot classes. In this work, we address the problem of long-tailed recognition wherein the training set is highly imbalanced and the test set is kept balanced. Differently from existing paradigms relying on data-resampling, cost-sensitive learning, online hard example mining, loss objective reshaping, and/or memory-based modeling, we propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition. We conduct extensive experiments to analyse the performance of the ensembles, and discover that in modern large-scale datasets, relative imbalance is a harder problem than data scarcity. The training and evaluation code is available at this https URL.

History

Preferred Citation

Saurabh Sharma, Ning Yu, Mario Fritz and Bernt Schiele. Long-Tailed Recognition Using Class-Balanced Experts. In: German Conference on Pattern Recognition (GCPR). 2020.

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

German Conference on Pattern Recognition (GCPR)

Legacy Posted Date

2021-02-18

Open Access Type

  • Green

BibTeX

@inproceedings{cispa_all_3366, title = "Long-Tailed Recognition Using Class-Balanced Experts", author = "Sharma, Saurabh and Yu, Ning and Fritz, Mario and Schiele, Bernt", booktitle="{German Conference on Pattern Recognition (GCPR)}", year="2020", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC