paper-with-me

홈 › Papers

Label-Aware Distribution Calibration for Long-tailed Classification

2021-11-09 · Chaozheng Wang, Shuzheng Gao, Cuiyun Gao, Pengyun Wang, Wenjie Pei, Lujia Pan, Zenglin Xu

Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail classes is the main challenge, which results in biased distribution estimation during training. Plenty of efforts have been devoted to ameliorating the challenge, including data re-sampling and synthesizing new training instances for tail classes. However, no prior research has exploited the transferable knowledge from head classes to tail classes for calibrating the distribution of tail classes. In this paper, we suppose that tail classes can be enriched by similar head classes and propose a novel distribution calibration approach named as label-Aware Distribution Calibration LADC. LADC transfers the statistics from relevant head classes to infer the distribution of tail classes. Sampling from calibrated distribution further facilitates re-balancing the classifier. Experiments on both image and text long-tailed datasets demonstrate that LADC significantly outperforms existing methods.The visualization also shows that LADC provides a more accurate distribution estimation.

📄 PDF Abstract BibTeX arXiv:2111.04901

Code (0)

등록된 구현이 없습니다.

Tasks

Classification

Similar Papers 제목 키워드 기반

Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition

2021-09-11 · Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren, Ben Glocker

Despite impressive accuracy, deep neural networks are often miscalibrated and tend to overly confident predictions. Recent techniques like temperature scaling (TS) and label smoothing (LS) show effectiveness in obtaining…

UCCNLP@SMM4H’22:Label distribution aware long-tailed learning with post-hoc posterior calibration applied to text classification

2022-10-01 · SMM4H (COLING) 2022 10 · Paul Trust, Provia Kadusabe, Ahmed Zahran, Rosane Minghim 외

The paper describes our submissions for the Social Media Mining for Health (SMM4H) workshop 2022 shared tasks. We participated in 2 tasks: (1) classification of adverse drug events (ADE) mentions in english tweets (Task-…

Classificationtext-classificationText Classification

Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution

2023-04-13 · CVPR 2023 1 · Jiahao Chen, Bing Su

How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ign…

Domain Adaptation

Improving Calibration for Long-Tailed Recognition

2021-04-01 · CVPR 2021 1 · Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia

Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still…

Long-tail LearningRepresentation Learning

Frequency-Aware Self-Supervised Long-Tailed Learning

2023-09-09 · Ci-Siang Lin, Min-Hung Chen, Yu-Chiang Frank Wang

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning appro…

Self-Supervised Learning