Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

• URL: http://arxiv.org/abs/2412.15477v1
• Date: Fri, 20 Dec 2024 01:11:30 GMT
• Title: Difficulty-aware Balancing Margin Loss for Long-tailed Recognition
• Authors: Minseok Son, Inyong Koo, Jinyoung Park, Changick Kim,
• Abstract summary: We propose a difficulty-aware balancing margin (DBM) loss, which considers both class imbalance and instance difficulty.<n>Our method seamlessly combines with existing approaches and consistently improves performance across various long-tailed recognition benchmarks.
• Score: 17.805309043663563
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition have attempted to rebalance biased learning using known sample distributions, primarily addressing different classification difficulties at the class level. However, these approaches often overlook the instance difficulty variation within each class. In this paper, we propose a difficulty-aware balancing margin (DBM) loss, which considers both class imbalance and instance difficulty. DBM loss comprises two components: a class-wise margin to mitigate learning bias caused by imbalanced class frequencies, and an instance-wise margin assigned to hard positive samples based on their individual difficulty. DBM loss improves class discriminativity by assigning larger margins to more difficult samples. Our method seamlessly combines with existing approaches and consistently improves performance across various long-tailed recognition benchmarks.

Related papers

• Identifying Key Challenges of Hardness-Based Resampling [0.5678271181959529]
  Performance gap across classes remains a persistent challenge in machine learning. One way to quantify class hardness is through sample complexity. Harder classes need substantially more samples to achieve generalization.
  arXiv  Detail & Related papers  (2025-04-09T16:45:57Z)
• DAFA: Distance-Aware Fair Adversarial Training [34.94780532071229]
  Under adversarial attacks, the majority of the model's predictions for samples from the worst class are biased towards classes similar to the worst class. We introduce the Distance-Aware Fair Adversarial training (DAFA) methodology, which addresses robust fairness by taking into account the similarities between classes.
  arXiv  Detail & Related papers  (2024-01-23T07:15:47Z)
• A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning [129.63326990812234]
  We propose a technique named data-dependent contraction to capture how modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment.
  arXiv  Detail & Related papers  (2023-10-07T09:15:08Z)
• Exploring Weight Balancing on Long-Tailed Recognition Problem [32.01426831450348]
  Recognition problems in long-tailed data, in which the sample size per class is heavily skewed, have gained importance. Weight balancing, which combines classical regularization techniques with two-stage training, has been proposed. We analyze weight balancing by focusing on neural collapse and the cone effect at each training stage.
  arXiv  Detail & Related papers  (2023-05-26T01:45:19Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure [2.7413469516930578]
  A large number of weighting methods essentially utilize the learning difficulty of training samples to calculate their weights. The learning difficulties of the samples are determined by multiple factors including noise level, imbalance degree, margin, and uncertainty. In this study, we theoretically prove that the generalization error of a sample can be used as a universal difficulty measure.
  arXiv  Detail & Related papers  (2023-01-12T07:28:32Z)
• Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition [5.977483447975081]
  We propose Difficulty-Net, which learns to predict the difficulty of classes using the model's performance in a meta-learning framework. We introduce two key concepts, namely the relative difficulty and the driver loss. Experiments on popular long-tailed datasets demonstrated the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-09-07T07:04:08Z)
• Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
  Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. We analyze the challenges these methods meet with the empirical experiment results. We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
  arXiv  Detail & Related papers  (2022-03-23T07:33:37Z)
• Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
  Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
  arXiv  Detail & Related papers  (2022-01-08T07:48:36Z)
• Fairness-aware Class Imbalanced Learning [57.45784950421179]
  We evaluate long-tail learning methods for tweet sentiment and occupation classification. We extend a margin-loss based approach with methods to enforce fairness.
  arXiv  Detail & Related papers  (2021-09-21T22:16:30Z)
• Long-Tailed Recognition Using Class-Balanced Experts [128.73438243408393]
  We propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition.
  arXiv  Detail & Related papers  (2020-04-07T20:57:44Z)

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.