Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation
This addresses the challenge of imbalanced data in real-world visual recognition, offering an incremental improvement for long-tailed classification tasks.
The paper tackles long-tailed classification by proposing GLAG, which uses Gradual Balanced Loss and adaptive feature generation to improve model robustness and augment tail classes, achieving state-of-the-art results on datasets like CIFAR100-LT, ImageNetLT, and iNaturalist.
The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG first learns a balanced and robust feature model with Gradual Balanced Loss, then fixes the feature model and augments the under-represented tail classes on the feature level with the knowledge from well-represented head classes. And the generated samples are mixed up with real training samples during training epochs. Gradual Balanced Loss is a general loss and it can combine with different decoupled training methods to improve the original performance. State-of-the-art results have been achieved on long-tail datasets such as CIFAR100-LT, ImageNetLT, and iNaturalist, which demonstrates the effectiveness of GLAG for long-tailed visual recognition.