Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective

By Muhammad Abdullah Jamal, Matthew A. Brown, Ming-Hsuan Yang, Liqiang Wang, Boqing Gong. 2020

305 citations recorded by the source corpus.

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We analyze this mismatch from a domain adaptation point of view. First of all, we connect existing class-balanced methods for long-tailed classification to target shift, a well-studied scenario in domain adaptation. The connection reveals that these methods implicitly assume that the training data and test data share the same class-conditioned distribution, which does not hold in general and especially for the tail classes. While a head class could contain abundant and diverse training examples that well represent the expected data at inference time, the tail classes are often short of representative training data. To this end, we propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach. We validate our approach with six benchmark datasets and three loss functions.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Pediatrics, Perinatology and Child Health, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (2020, background): “Other more complicated learning methods ( e.g ., meta-learning [63, 29, 32], causal inference [58], Bayesian methods [34], etc .) are also used to deal with long-tail data.”
Disentangling Label Distribution for Long-tailed Visual Recognition (2020, background): “[24] applies domain adaptation on learning tail class representation.”
Rethinking the Value of Labels for Improving Class-Imbalanced Learning (2020, background): “Imbalanced data is ubiquitous in the real world, where large-scale datasets often exhibit long-tailed label distributions [1,5,24,33].”
Parametric Contrastive Learning (2021, methodology): “Re-weighting [23, 24, 51, 39, 42, 26] the loss functions is an alternative way to rebalance by either enlarging weights on more challenging and sparse classes or randomly ignoring gradients from high-frequency classes [44].”
Long-tail learning via logit adjustment (2020, background): “, 2020); or (iii) the training procedure of a model, for example by modifying the loss function (Zhang et al., 2017; Cui et al., 2019; Cao et al., 2019; Tan et al., 2020; Jamal et al., 2020).”
Balanced Knowledge Distillation for Long-tailed Learning (2021, background): “Many approaches [19, 40, 51] design additional modules or meta-network to transfer knowledge, e.”
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect (2020, unknown): “Instead of hacking the prior distribution of classes, focusing on the hard samples also alleviates the long-tailed issue, e.g. , using meta-learning to find the conditional weights for each samples [31], enhancing the samples of hard categories by group softmax [32].”
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning (2021, methodology): “Similar observations are made on other SSL algorithms, and also on fully-supervised class-imbalanced learning [19].”
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts (2020, unknown): “Another major direction to learning balance is transferring knowledge from head to tail classes (Liu et al., 2019; Zhu & Yang, 2020; Kang et al., 2020; Jamal et al., 2020; Wang et al., 2017).”