Long-tail Detection with Effective Class-Margins
This addresses the challenge of improving detection performance for rare classes in long-tailed datasets, which is crucial for real-world applications where fine-grained objects are infrequent.
The paper tackles the problem of data imbalance in large-scale object detection and instance segmentation, particularly for long-tailed datasets, by introducing the Effective Class-Margin Loss (ECM), which outperforms other methods on the LVIS v1 benchmark.
Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector that performs well for all classes and not just the most frequent ones. In this paper, we provide a theoretical understanding of the long-trail detection problem. We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error on a long-tailed object detection training set. We optimize margin-based binary classification error with a novel surrogate objective called \textbf{Effective Class-Margin Loss} (ECM). The ECM loss is simple, theoretically well-motivated, and outperforms other heuristic counterparts on LVIS v1 benchmark over a wide range of architecture and detectors. Code is available at \url{https://github.com/janghyuncho/ECM-Loss}.