Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks

TLDR

Long‑tailed visual recognition has advanced mainly through complex paradigms, yet simple training refinements—though effective—can conflict and lack a scientific guideline. This work compiles existing tricks, systematically evaluates them, and proposes a class‑activation‑map‑based augmentation to guide users toward optimal combinations. The authors conduct extensive experiments, introduce the augmentation method, and release open‑source code to facilitate reproducibility. The resulting combination surpasses state‑of‑the‑art performance on four long‑tailed benchmarks, including ImageNet‑LT and iNaturalist 2018.

Abstract

In recent years, visual recognition on challenging long-tailed distributions, where classes often exhibit extremely imbalanced frequencies, has made great progress mostly based on various complex paradigms (e.g., meta learning). Apart from these complex methods, simple refinements on training procedures also make contributions. These refinements, also called tricks, are minor but effective, such as adjustments in the data distribution or loss functions. However, different tricks might conflict with each other. If users apply these long-tail related tricks inappropriately, it could cause worse recognition accuracy than expected. Unfortunately, there has not been a scientific guideline of these tricks in the literature. In this paper, we first collect existing tricks in long-tailed visual recognition and then perform extensive and systematic experiments, in order to give a detailed experimental guideline and obtain an effective combination of these tricks. Furthermore, we also propose a novel data augmentation approach based on class activation maps for long-tailed recognition, which can be friendly combined with re-sampling methods and shows excellent results. By assembling these tricks scientifically, we can outperform state-of-the-art methods on four long-tailed benchmark datasets, including ImageNet-LT and iNaturalist 2018. Our code is open-source and available at https://github.com/zhangyongshun/BagofTricks-LT.