Balanced Product of Calibrated Experts for Long-Tailed Recognition
Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited generalization over the tail classes. If the test distribution differs from the training distribution, e.g. uniform versus long-tailed, the problem of the distribution shift needs to be addressed. A recent line of work proposes learning multiple diverse experts to tackle this issue. Ensemble diversity is encouraged by various techniques, e.g. by specializing different experts in the head and the tail classes. In this work, we take an analytical approach and extend the notion of logit adjustment to ensembles to form a Balanced Product of Experts (BalPoE). BalPoE combines a family of experts with different test-time target distributions, generalizing several previous approaches. We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions, by proving that the ensemble is Fisher-consistent for minimizing the balanced error. Our theoretical analysis shows that our balanced ensemble requires calibrated experts, which we achieve in practice using mixup. We conduct extensive experiments and our method obtains new state-of-the-art results on three long-tailed datasets: CIFAR-100-LT, ImageNet-LT, and iNaturalist-2018. Our code is available at https://github.com/emasa/BalPoE-CalibratedLT.
Code (2)
Tasks
Long-tail LearningLong-tail Learning on CIFAR-10-LT (ρ=100)Representation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Long-Tailed Recognition Using Class-Balanced Experts
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges…
Long-tail LearningLTE4G: Long-Tail Experts for Graph Neural Networks
Existing Graph Neural Networks (GNNs) usually assume a balanced situation where both the class distribution and the node degree distribution are balanced. However, in real-world situations, we often encounter cases where…
Knowledge DistillationNode ClassificationBalancing Domain Experts for Long-Tailed Camera-Trap Recognition
Label distributions in camera-trap images are highly imbalanced and long-tailed, resulting in neural networks tending to be biased towards head-classes that appear frequently. Although long-tail learning has been extreme…
Long-tail LearningOptical Flow EstimationGlobal Balanced Experts for Federated Long-Tailed Learning
Federated learning (FL) is a prevalent distributed machine learning approach that enables collaborative training of a global model across multiple devices without sharing local data. However, the presence of long-tai…
Federated LearningPrivacy PreservingNCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition
Long-tailed visual recognition has received increasing attention in recent years. Due to the extremely imbalanced data distribution in long-tailed learning, the learning process shows great uncertainties. For example, th…