Learning Imbalanced Datasets with Maximum Margin Loss

2022-06-11 · Haeyong Kang, Thang Vu, Chang D. Yoo

A learning algorithm referred to as Maximum Margin (MM) is proposed for considering the class-imbalance data learning issue: the trained model tends to predict the majority of classes rather than the minority ones. That is, underfitting for minority classes seems to be one of the challenges of generalization. For a good generalization of the minority classes, we design a new Maximum Margin (MM) loss function, motivated by minimizing a margin-based generalization bound through the shifting decision bound. The theoretically-principled label-distribution-aware margin (LDAM) loss was successfully applied with prior strategies such as re-weighting or re-sampling along with the effective training schedule. However, they did not investigate the maximum margin loss function yet. In this study, we investigate the performances of two types of hard maximum margin-based decision boundary shift with LDAM's training schedule on artificially imbalanced CIFAR-10/100 for fair comparisons and effectiveness.

📄 PDF Abstract BibTeX arXiv:2206.05380

Code (1)

ihaeyong/maximum-margin-ldam 공식 구현 pytorch

Enlarged Large Margin Loss for Imbalanced Classification

2023-06-15 · Sota Kato, Kazuhiro Hotta

We propose a novel loss function for imbalanced classification. LDAM loss, which minimizes a margin-based generalization bound, is widely utilized for class-imbalanced image classification. Although, by using LDAM loss, …

Classification image-classification Image Classification imbalanced classification

Max-margin Class Imbalanced Learning with Gaussian Affinity

2019-01-23 · Munawar Hayat, Salman Khan, Waqas Zamir, Jianbing Shen 외

Real-world object classes appear in imbalanced ratios. This poses a significant challenge for classifiers which get biased towards frequent classes. We hypothesize that improving the generalization capability of a classi…

Classification Clustering Diversity General Classification

Gaussian Affinity for Max-Margin Class Imbalanced Learning

2019-10-01 · ICCV 2019 10 · Munawar Hayat, Salman Khan, Syed Waqas Zamir, Jianbing Shen 외

Classification Clustering Diversity General Classification

Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition

2019-10-01 · ICCV 2019 10 · Bingyu Liu, Weihong Deng, Yaoyao Zhong, Mei Wang 외

Recently, large-margin softmax loss methods, such as angular softmax loss (SphereFace), large margin cosine loss (CosFace), and additive angular margin loss (ArcFace), have demonstrated impressive performance on deep fac…

Face Recognition Q-Learning reinforcement-learning Reinforcement Learning+1

Maximum-Margin Hamming Hashing

2019-10-01 · ICCV 2019 10 · Rong Kang, Yue Cao, Mingsheng Long, Jianmin Wang 외

Deep hashing enables computation and memory efficient image search through end-to-end learning of feature representations and binary codes. While linear scan over binary hash codes is more efficient than over the high-di…

Deep Hashing Image Retrieval Retrieval