Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach

• URL: http://arxiv.org/abs/2407.03146v3
• Date: Tue, 25 Mar 2025 09:05:02 GMT
• Title: Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach
• Authors: Yunpeng Jiang, Paul Weng, Yutong Ban,
• Abstract summary: We propose CLAM, a CLAss-dependent Multiplicative-weights method to counteract the unfair effect of data augmentation on classification performance.<n>Our results show that the performance of learned classifiers is indeed more fairly distributed over classes, with only limited impact on the average accuracy.
• Score: 7.05832012052375
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data augmentation is widely applied and has shown its benefits in different machine learning tasks. However, as recently observed, it may have an unfair effect in multi-class classification. While data augmentation generally improves the overall performance (and therefore is beneficial for many classes), it can actually be detrimental for other classes, which can be problematic in some application domains. In this paper, to counteract this phenomenon, we propose CLAM, a CLAss-dependent Multiplicative-weights method. To derive it, we first formulate the training of a classifier as a non-linear optimization problem that aims at simultaneously maximizing the individual class performances and balancing them. By rewriting this optimization problem as an adversarial two-player game, we propose a novel multiplicative weight algorithm, for which we prove the convergence. Interestingly, our formulation also reveals that the class-dependent effects of data augmentation is not due to data augmentation only, but is in fact a general phenomenon. Our empirical results over five datasets demonstrate that the performance of learned classifiers is indeed more fairly distributed over classes, with only limited impact on the average accuracy.

Related papers

• Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning [12.67816343247008]
  Class-incremental Learning enables the model to incrementally absorb knowledge from new classes. When the model optimize with new classes, the knowledge of previous classes is inevitably erased, leading to catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-03-25T09:51:04Z)
• CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection [22.11525246060963]
  We propose Class-Aware Teacher (CAT) to address the class bias issue in the domain adaptation setting. In our work, we approximate the class relationships with our Inter-Class Relation module (ICRm) and exploit it to reduce the bias within the model. Experiments conducted on various datasets and ablation studies show that our method is able to address the class bias in the domain adaptation setting.
  arXiv  Detail & Related papers  (2024-03-28T10:02:08Z)
• Classes Are Not Equal: An Empirical Study on Image Recognition Fairness [100.36114135663836]
  We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets. Our findings reveal that models tend to exhibit greater prediction biases for classes that are more challenging to recognize. Data augmentation and representation learning algorithms improve overall performance by promoting fairness to some degree in image classification.
  arXiv  Detail & Related papers  (2024-02-28T07:54:50Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Understanding the Detrimental Class-level Effects of Data Augmentation [63.1733767714073]
  achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. We present a framework for understanding how DA interacts with class-level learning dynamics. We show that simple class-conditional augmentation strategies improve performance on the negatively affected classes.
  arXiv  Detail & Related papers  (2023-12-07T18:37:43Z)
• Review of Methods for Handling Class-Imbalanced in Classification Problems [0.0]
  In some cases, one class contains the majority of examples while the other, which is frequently the more important class, is nevertheless represented by a smaller proportion of examples. The article examines the most widely used methods for addressing the problem of learning with a class imbalance, including data-level, algorithm-level, hybrid, cost-sensitive learning, and deep learning.
  arXiv  Detail & Related papers  (2022-11-10T10:07:10Z)
• EquiMod: An Equivariance Module to Improve Self-Supervised Learning [77.34726150561087]
  Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. We introduce EquiMod a generic equivariance module that structures the learned latent space.
  arXiv  Detail & Related papers  (2022-11-02T16:25:54Z)
• Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
  Underlying data structures are often exploited to improve the solution of learning tasks. Data augmentation induces these symmetries during training by applying multiple transformations to the input data. This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
  arXiv  Detail & Related papers  (2022-09-29T18:11:01Z)
• Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views [22.47152165975219]
  A data augmentation module is utilized in contrastive learning to transform the given data example into two views. This paper proposes a general method to alleviate these two problems by considering where and what to contrast in a general contrastive learning framework.
  arXiv  Detail & Related papers  (2022-06-01T04:30:46Z)
• Regularising for invariance to data augmentation improves supervised learning [82.85692486314949]
  We show that using multiple augmentations per input can improve generalisation. We propose an explicit regulariser that encourages this invariance on the level of individual model predictions.
  arXiv  Detail & Related papers  (2022-03-07T11:25:45Z)
• Multi-Class Classification from Single-Class Data with Confidences [90.48669386745361]
  We propose an empirical risk minimization framework that is loss-/model-/optimizer-independent. We show that our method can be Bayes-consistent with a simple modification even if the provided confidences are highly noisy.
  arXiv  Detail & Related papers  (2021-06-16T15:38:13Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Class-Incremental Learning with Generative Classifiers [6.570917734205559]
  We propose a new strategy for class-incremental learning: generative classification. Our proposal is to learn the joint distribution p(x,y), factorized as p(x|y)p(y), and to perform classification using Bayes' rule. As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned.
  arXiv  Detail & Related papers  (2021-04-20T16:26:14Z)
• Few-Shot Incremental Learning with Continually Evolved Classifiers [46.278573301326276]
  Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. We propose a Continually Evolved CIF ( CEC) that employs a graph model to propagate context information between classifiers for adaptation.
  arXiv  Detail & Related papers  (2021-04-07T10:54:51Z)
• Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View [82.80085730891126]
  We provide the first modernally precise analysis of linear multiclass classification. Our analysis reveals that the classification accuracy is highly distribution-dependent. The insights gained may pave the way for a precise understanding of other classification algorithms.
  arXiv  Detail & Related papers  (2020-11-16T05:17:29Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• Robustifying Binary Classification to Adversarial Perturbation [45.347651499585055]
  In this paper we consider the problem of binary classification with adversarial perturbations. We introduce a generalization to the max-margin classifier which takes into account the power of the adversary in manipulating the data. Under some mild assumptions on the loss function, we theoretically show that the gradient descents converge to the RM classifier in its direction.
  arXiv  Detail & Related papers  (2020-10-29T07:20:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.