Investigate the Essence of Long-Tailed Recognition from a Unified Perspective

• URL: http://arxiv.org/abs/2107.03758v1
• Date: Thu, 8 Jul 2021 11:08:40 GMT
• Title: Investigate the Essence of Long-Tailed Recognition from a Unified Perspective
• Authors: Lei Liu and Li Liu
• Abstract summary: deep recognition models often suffer from long-tailed data distributions due to heavy imbalanced sample number across categories. In this work, we demonstrate that long-tailed recognition suffers from both sample number and category similarity.
• Score: 11.080317683184363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As the data scale grows, deep recognition models often suffer from long-tailed data distributions due to the heavy imbalanced sample number across categories. Indeed, real-world data usually exhibit some similarity relation among different categories (e.g., pigeons and sparrows), called category similarity in this work. It is doubly difficult when the imbalance occurs between such categories with similar appearances. However, existing solutions mainly focus on the sample number to re-balance data distribution. In this work, we systematically investigate the essence of the long-tailed problem from a unified perspective. Specifically, we demonstrate that long-tailed recognition suffers from both sample number and category similarity. Intuitively, using a toy example, we first show that sample number is not the unique influence factor for performance dropping of long-tailed recognition. Theoretically, we demonstrate that (1) category similarity, as an inevitable factor, would also influence the model learning under long-tailed distribution via similar samples, (2) using more discriminative representation methods (e.g., self-supervised learning) for similarity reduction, the classifier bias can be further alleviated with greatly improved performance. Extensive experiments on several long-tailed datasets verify the rationality of our theoretical analysis, and show that based on existing state-of-the-arts (SOTAs), the performance could be further improved by similarity reduction. Our investigations highlight the essence behind the long-tailed problem, and claim several feasible directions for future work.

Related papers

• Pooling Image Datasets With Multiple Covariate Shift and Imbalance [22.53402104452306]
  We show how viewing this problem from the perspective of Category theory provides a simple and effective solution. We show the effectiveness of this approach via extensive experiments on real datasets.
  arXiv  Detail & Related papers  (2024-03-05T02:20:33Z)
• Class-Balancing Diffusion Models [57.38599989220613]
  Class-Balancing Diffusion Models (CBDM) are trained with a distribution adjustment regularizer as a solution. Our method benchmarked the generation results on CIFAR100/CIFAR100LT dataset and shows outstanding performance on the downstream recognition task.
  arXiv  Detail & Related papers  (2023-04-30T20:00:14Z)
• Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts [3.7819322027528113]
  We propose a new regularization using the supervised contrastive learning to prevent such overfitting and to train models that do not degrade their performance under the distribution shifts. Experiments on benchmark datasets that emulate distribution shifts, including subpopulation shift and domain generalization, demonstrate the advantage of the proposed method.
  arXiv  Detail & Related papers  (2023-04-07T01:45:09Z)
• Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets [53.34152466646884]
  In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
  arXiv  Detail & Related papers  (2022-03-29T04:54:06Z)
• An Empirical Study on the Joint Impact of Feature Selection and Data Resampling on Imbalance Classification [4.506770920842088]
  This study focuses on the synergy between feature selection and data resampling for imbalance classification. We conduct a large amount of experiments on 52 publicly available datasets, using 9 feature selection methods, 6 resampling approaches for class imbalance learning, and 3 well-known classification algorithms.
  arXiv  Detail & Related papers  (2021-09-01T06:01:51Z)
• The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification [13.376247652484274]
  In lung nodule classification, many works report results on the publicly available LIDC dataset. In theory, this should allow a direct comparison of the performance of proposed methods and assess the impact of individual contributions. We find that each employs a different data selection process, leading to largely varying total number of samples and ratios between benign and malignant cases. We show that specific choices can have severe impact on the data distribution where it may be possible to achieve superior performance on one sample distribution but not on another.
  arXiv  Detail & Related papers  (2021-08-11T18:07:07Z)
• 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)
• Few-shot Visual Reasoning with Meta-analogical Contrastive Learning [141.2562447971]
  We propose to solve a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning. We extract structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning. We validate our method on RAVEN dataset, on which it outperforms state-of-the-art method, with larger gains when the training data is scarce.
  arXiv  Detail & Related papers  (2020-07-23T14:00:34Z)
• Learning from Aggregate Observations [82.44304647051243]
  We study the problem of learning from aggregate observations where supervision signals are given to sets of instances. We present a general probabilistic framework that accommodates a variety of aggregate observations. Simple maximum likelihood solutions can be applied to various differentiable models.
  arXiv  Detail & Related papers  (2020-04-14T06:18:50Z)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)

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.