paper-with-me

홈 › Papers

Decoupled Training for Long-Tailed Classification With Stochastic Representations

2023-04-19 · Giung Nam, Sunguk Jang, Juho Lee

Decoupling representation learning and classifier learning has been shown to be effective in classification with long-tailed data. There are two main ingredients in constructing a decoupled learning scheme; 1) how to train the feature extractor for representation learning so that it provides generalizable representations and 2) how to re-train the classifier that constructs proper decision boundaries by handling class imbalances in long-tailed data. In this work, we first apply Stochastic Weight Averaging (SWA), an optimization technique for improving the generalization of deep neural networks, to obtain better generalizing feature extractors for long-tailed classification. We then propose a novel classifier re-training algorithm based on stochastic representation obtained from the SWA-Gaussian, a Gaussian perturbed SWA, and a self-distillation strategy that can harness the diverse stochastic representations based on uncertainty estimates to build more robust classifiers. Extensive experiments on CIFAR10/100-LT, ImageNet-LT, and iNaturalist-2018 benchmarks show that our proposed method improves upon previous methods both in terms of prediction accuracy and uncertainty estimation.

📄 PDF Abstract BibTeX arXiv:2304.09426

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationRepresentation Learning

Methods 이 논문이 사용한 방법론

Stochastic Weight Averaging Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or…

Similar Papers 제목 키워드 기반

Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation

2022-02-28 · Zihan Zhang, Xiang Xiang

The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate …

Long-tail Learning

You Only Need End-to-End Training for Long-Tailed Recognition

2021-12-11 · Zhiwei Zhang

The generalization gap on the long-tailed data sets is largely owing to most categories only occupying a few training samples. Decoupled training achieves better performance by training backbone and classifier separately…

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

2020-12-15 · CVPR 2021 1 · Jingru Tan, Xin Lu, Gang Zhang, Changqing Yin 외

Recently proposed decoupled training methods emerge as a dominant paradigm for long-tailed object detection. But they require an extra fine-tuning stage, and the disjointed optimization of representation and classifier m…

Instance SegmentationLong-tailed Object Detectionobject-detectionObject Detection

Learning of Visual Relations: The Devil is in the Tails

2021-08-22 · ICCV 2021 10 · Alakh Desai, Tz-Ying Wu, Subarna Tripathi, Nuno Vasconcelos

Significant effort has been recently devoted to modeling visual relations. This has mostly addressed the design of architectures, typically by adding parameters and increasing model complexity. However, visual relation l…

Graph GenerationScene Graph Generation

Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning

2023-01-25 · Wenkai Yang, Deli Chen, Hao Zhou, Fandong Meng 외

Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner. However, the data samples usually fol…

Federated LearningPrivacy Preserving