.png){kind=icon}
.png){kind=icon}
Return
Reviving undersampling for long-tailed learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111200.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The training datasets used in long-tailed recognition are extremely unbalanced, resulting insignificant variation in per-class accuracy across categories. Prior works mostly used average accuracy to evaluate their algorithms, which easily ignores those worst-performing categories. In this paper, we aim to enhance the accuracy of the worst-performing categories and utilize the harmonic mean and geometric mean to assess the model's performance. We revive the balanced undersampling idea to achieve this goal. In few-shot learning, balanced subsets are few-shot and will surely under-fit, hence it is not used in modern long-tailed learning. But, we find that it produces a more equitable distribution of accuracy across categories with much higher harmonic and geometric mean accuracy, but with lower average accuracy. Moreover, we devise a straightforward model ensemble strategy, which does not result in any additional overhead and achieves improved harmonic and geometric mean while keeping the average accuracy almost intact when compared to state-of-the-art longtailed learning methods. We validate the effectiveness of our approach on widely utilized benchmark datasets for long-tailed learning. Our code is at https://github.com/yuhao318/BTM/.
Keywords:
Image classification
Long-tailed learning
Undersampling