Distributional Robustness Loss for Long-tail Learning

ICCV 2021  ·  Dvir Samuel, Gal Chechik ·

Real-world data is often unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. To address unbalanced data, most studies try balancing the data, the loss, or the classifier to reduce classification bias towards head classes. Far less attention has been given to the latent representations learned with unbalanced data. We show that the feature extractor part of deep networks suffers greatly from this bias. We propose a new loss based on robustness theory, which encourages the model to learn high-quality representations for both head and tail classes. While the general form of the robustness loss may be hard to compute, we further derive an easy-to-compute upper bound that can be minimized efficiently. This procedure reduces representation bias towards head classes in the feature space and achieves new SOTA results on CIFAR100-LT, ImageNet-LT, and iNaturalist long-tail benchmarks. We find that training with robustness increases recognition accuracy of tail classes while largely maintaining the accuracy of head classes. The new robustness loss can be combined with various classifier balancing techniques and can be applied to representations at several layers of the deep model.

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract
No code implementations yet. Submit your code now
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Long-tail Learning CIFAR-100-LT (ρ=10) DRO-LT Error Rate 36.59 # 17
Long-tail Learning CIFAR-100-LT (ρ=100) DRO-LT Error Rate 52.67 # 35
Long-tail Learning ImageNet-LT DRO-LT Top-1 Accuracy 53.5 # 38

Methods


No methods listed for this paper. Add relevant methods here