Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoon, Youngseok, Hong, Sangwoo, Joo, Hyungjun, Qin, Yao, Jeong, Haewon, Lee, Jungwoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913719343120384
author Yoon, Youngseok
Hong, Sangwoo
Joo, Hyungjun
Qin, Yao
Jeong, Haewon
Lee, Jungwoo
author_facet Yoon, Youngseok
Hong, Sangwoo
Joo, Hyungjun
Qin, Yao
Jeong, Haewon
Lee, Jungwoo
contents Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform. Existing methods typically detour the problem by i) adjusting a loss function, ii) decoupling classifier learning, or iii) proposing a new multi-head architecture called experts. In this paper, we tackle the problem from a different perspective to augment a training dataset to enhance the sample diversity of minority classes. Specifically, our method, namely Confusion-Pairing Mixup (CP-Mix), estimates the confusion distribution of the model and handles the data deficiency problem by augmenting samples from confusion pairs in real-time. In this way, CP-Mix trains the model to mitigate its weakness and distinguish a pair of classes it frequently misclassifies. In addition, CP-Mix utilizes a novel mixup formulation to handle the bias in decision boundaries that originated from the imbalanced dataset. Extensive experiments demonstrate that CP-Mix outperforms existing methods for long-tailed image recognition and successfully relieves the confusion of the classifier.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
Yoon, Youngseok
Hong, Sangwoo
Joo, Hyungjun
Qin, Yao
Jeong, Haewon
Lee, Jungwoo
Computer Vision and Pattern Recognition
Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform. Existing methods typically detour the problem by i) adjusting a loss function, ii) decoupling classifier learning, or iii) proposing a new multi-head architecture called experts. In this paper, we tackle the problem from a different perspective to augment a training dataset to enhance the sample diversity of minority classes. Specifically, our method, namely Confusion-Pairing Mixup (CP-Mix), estimates the confusion distribution of the model and handles the data deficiency problem by augmenting samples from confusion pairs in real-time. In this way, CP-Mix trains the model to mitigate its weakness and distinguish a pair of classes it frequently misclassifies. In addition, CP-Mix utilizes a novel mixup formulation to handle the bias in decision boundaries that originated from the imbalanced dataset. Extensive experiments demonstrate that CP-Mix outperforms existing methods for long-tailed image recognition and successfully relieves the confusion of the classifier.
title Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.07621