paper-with-me

홈 › Papers

Balanced Product of Calibrated Experts for Long-Tailed Recognition

2022-06-10 · CVPR 2023 1 · Emanuel Sanchez Aimar, Arvi Jonnarth, Michael Felsberg, Marco Kuhlmann

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.

📄 PDF Abstract BibTeX arXiv:2206.05260

Code (2)

emasa/balpoe-calibratedlt 공식 구현 pytorch
emasa/adello-ltssl pytorch

Tasks

Long-tail LearningLong-tail Learning on CIFAR-10-LT (ρ=100)Representation Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Long-Tailed Recognition Using Class-Balanced Experts

2020-04-07 · Saurabh Sharma, Ning Yu, Mario Fritz, Bernt Schiele

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 Learning

LTE4G: Long-Tail Experts for Graph Neural Networks

2022-08-22 · Sukwon Yun, Kibum Kim, Kanghoon Yoon, Chanyoung Park

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 Classification

Balancing Domain Experts for Long-Tailed Camera-Trap Recognition

2022-02-15 · Byeongjun Park, JeongSoo Kim, Seungju Cho, Heeseon Kim 외

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 Estimation

Global Balanced Experts for Federated Long-Tailed Learning

2023-01-01 · ICCV 2023 1 · Yaopei Zeng, Lei Liu, Li Liu, Li Shen 외

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 Preserving

NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition

2023-06-29 · Zichang Tan, Jun Li, Jinhao Du, Jun Wan 외

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…