BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learning

by   Wujian Peng, et al.

Exploring a substantial amount of unlabeled data, semi-supervised learning (SSL) boosts the recognition performance when only a limited number of labels are provided. However, traditional methods assume that the data distribution is class-balanced, which is difficult to achieve in reality due to the long-tailed nature of real-world data. While the data imbalance problem has been extensively studied in supervised learning (SL) paradigms, directly transferring existing approaches to SSL is nontrivial, as prior knowledge about data distribution remains unknown in SSL. In light of this, we propose Balanced Memory Bank (BMB), a semi-supervised framework for long-tailed recognition. The core of BMB is an online-updated memory bank that caches historical features with their corresponding pseudo labels, and the memory is also carefully maintained to ensure the data therein are class-rebalanced. Additionally, an adaptive weighting module is introduced to work jointly with the memory bank so as to further re-calibrate the biased training process. We conduct experiments on multiple datasets and demonstrate, among other things, that BMB surpasses state-of-the-art approaches by clear margins, for example 8.2% on the 1% labeled subset of ImageNet127 (with a resolution of 64×64) and 4.3% on the 50% labeled subset of ImageNet-LT.


page 1

page 2

page 3

page 4


Semi-supervised Long-tailed Recognition using Alternate Sampling

Main challenges in long-tailed recognition come from the imbalanced data...

Align, Distill, and Augment Everything All at Once for Imbalanced Semi-Supervised Learning

Addressing the class imbalance in long-tailed semi-supervised learning (...

Transfer and Share: Semi-Supervised Learning from Long-Tailed Data

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-im...

Debiased Learning from Naturally Imbalanced Pseudo-Labels for Zero-Shot and Semi-Supervised Learning

This work studies the bias issue of pseudo-labeling, a natural phenomeno...

One-Class Classification for Wafer Map using Adversarial Autoencoder with DSVDD Prior

Recently, semiconductors' demand has exploded in virtual reality, smartp...

BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets

Current semi-supervised learning (SSL) methods assume a balance between ...

Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South Central Andes

The detection of ancient settlements is a key focus in landscape archaeo...

Please sign up or login with your details

Forgot password? Click here to reset