Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier

By Tz-Ying Wu, Pedro Morgado, Pei Wang, Chih-Hui Ho, Nuno Vasconcelos. 2020

59 citations recorded by the source corpus.

Long-tail recognition tackles the natural non-uniformly distributed data in real-world scenarios. While modern classifiers perform well on populated classes, its performance degrades significantly on tail classes. Humans, however, are less affected by this since, when confronted with uncertain examples, they simply opt to provide coarser predictions. Motivated by this, a deep realistic taxonomic classifier (Deep-RTC) is proposed as a new solution to the long-tail problem, combining realism with hierarchical predictions. The model has the option to reject classifying samples at different levels of the taxonomy, once it cannot guarantee the desired performance. Deep-RTC is implemented with a stochastic tree sampling during training to simulate all possible classification conditions at finer or coarser levels and a rejection mechanism at inference time. Experiments on the long-tailed version of four datasets, CIFAR100, AWA2, Imagenet, and iNaturalist, demonstrate that the proposed approach preserves more information on all classes with different popularity levels. Deep-RTC also outperforms the state-of-the-art methods in longtailed recognition, hierarchical classification, and learning with rejection literature using the proposed correctly predicted bits (CPB) metric.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

  1. Shipeng Yan
  2. Songyang Zhang
  3. Zeming Li
  4. Xuming He
  5. Jian‐Yuan Sun
  6. Kaiming He
  7. Liang-Chieh Chen
  8. Da-Wei Zhou

Citations in the corpus