Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

• URL: http://arxiv.org/abs/2007.09654v4
• Date: Sat, 4 Dec 2021 02:47:46 GMT
• Title: Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
• Authors: Tong Wu, Qingqiu Huang, Ziwei Liu, Yu Wang, Dahua Lin
• Abstract summary: We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. The Distribution-Balanced Loss tackles these issues through two key modifications to the standard binary cross-entropy loss. Experiments on both Pascal VOC and COCO show that the models trained with this new loss function achieve significant performance gains.
• Score: 98.74153364118898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional single-label classification problem, multi-label recognition problems are often more challenging due to two significant issues, namely the co-occurrence of labels and the dominance of negative labels (when treated as multiple binary classification problems). The Distribution-Balanced Loss tackles these issues through two key modifications to the standard binary cross-entropy loss: 1) a new way to re-balance the weights that takes into account the impact caused by label co-occurrence, and 2) a negative tolerant regularization to mitigate the over-suppression of negative labels. Experiments on both Pascal VOC and COCO show that the models trained with this new loss function achieve significant performance gains over existing methods. Code and models are available at: https://github.com/wutong16/DistributionBalancedLoss .

Related papers

• Rebalancing Multi-Label Class-Incremental Learning [17.921329790170265]
  We propose a Rebalance framework for both the Loss and Label levels (RebLL) AKD is proposed to rebalance at the loss level by emphasizing the negative label learning in classification loss. OR is designed for label rebalance, which restores the original class distribution in memory by online relabeling the missing classes.
  arXiv  Detail & Related papers  (2024-08-22T07:04:22Z)
• Multi-Label Learning with Stronger Consistency Guarantees [30.389055604165222]
  We present a detailed study of surrogate losses and algorithms for multi-label learning, supported by $H$-consistency bounds. We introduce a novel surrogate loss, multi-label logistic loss, that accounts for label correlations and benefits from label-independent $H$-consistency bounds. We prove that this family of surrogate losses benefits from $H$-consistency bounds, and thus Bayes-consistency, across any general multi-label loss.
  arXiv  Detail & Related papers  (2024-07-18T17:51:02Z)
• Confidence Self-Calibration for Multi-Label Class-Incremental Learning [21.104984143597882]
  Partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training. This issue leads to a proliferation of false-positive errors due to erroneously high confidence multi-label predictions. We propose a Confidence Self-Calibration (CSC) approach to refine multi-label confidence calibration in MLCIL.
  arXiv  Detail & Related papers  (2024-03-19T09:14:52Z)
• Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning [97.88458953075205]
  Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data. This paper proposes a novel solution called Class-Aware Pseudo-Labeling (CAP) that performs pseudo-labeling in a class-aware manner.
  arXiv  Detail & Related papers  (2023-05-04T12:52:18Z)
• PercentMatch: Percentile-based Dynamic Thresholding for Multi-Label Semi-Supervised Classification [64.39761523935613]
  We propose a percentile-based threshold adjusting scheme to dynamically alter the score thresholds of positive and negative pseudo-labels for each class during the training. We achieve strong performance on Pascal VOC2007 and MS-COCO datasets when compared to recent SSL methods.
  arXiv  Detail & Related papers  (2022-08-30T01:27:48Z)
• Unbiased Loss Functions for Multilabel Classification with Missing Labels [2.1549398927094874]
  Missing labels are a ubiquitous phenomenon in extreme multi-label classification (XMC) tasks. This paper derives the unique unbiased estimators for the different multilabel reductions.
  arXiv  Detail & Related papers  (2021-09-23T10:39:02Z)
• Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces [64.23172847182109]
  We show that different negative sampling schemes implicitly trade-off performance on dominant versus rare labels. We provide a unified means to explicitly tackle both sampling bias, arising from working with a subset of all labels, and labeling bias, which is inherent to the data due to label imbalance.
  arXiv  Detail & Related papers  (2021-05-12T15:40:13Z)
• DropLoss for Long-Tail Instance Segmentation [56.162929199998075]
  We develop DropLoss, a novel adaptive loss to compensate for the imbalance between rare and frequent categories. We show state-of-the-art mAP across rare, common, and frequent categories on the LVIS dataset.
  arXiv  Detail & Related papers  (2021-04-13T17:59:22Z)
• Long-tail learning via logit adjustment [67.47668112425225]
  Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution. This poses a challenge for generalisation on such labels, and also makes na"ive learning biased towards dominant labels. We present two simple modifications of standard softmax cross-entropy training to cope with these challenges.
  arXiv  Detail & Related papers  (2020-07-14T19:27:13Z)

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.