Understanding CNN Fragility When Learning With Imbalanced Data

• URL: http://arxiv.org/abs/2210.09465v1
• Date: Mon, 17 Oct 2022 22:40:06 GMT
• Title: Understanding CNN Fragility When Learning With Imbalanced Data
• Authors: Damien Dablain, Kristen N. Jacobson, Colin Bellinger, Mark Roberts and Nitesh Chawla
• Abstract summary: Convolutional neural networks (CNNs) have achieved impressive results on imbalanced image data, but they still have difficulty generalizing to minority classes. We focus on their latent features to demystify CNN decisions on imbalanced data. We show that important information regarding the ability of a neural network to generalize to minority classes resides in the class top-K CE and FE.
• Score: 1.1444576186559485
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional neural networks (CNNs) have achieved impressive results on imbalanced image data, but they still have difficulty generalizing to minority classes and their decisions are difficult to interpret. These problems are related because the method by which CNNs generalize to minority classes, which requires improvement, is wrapped in a blackbox. To demystify CNN decisions on imbalanced data, we focus on their latent features. Although CNNs embed the pattern knowledge learned from a training set in model parameters, the effect of this knowledge is contained in feature and classification embeddings (FE and CE). These embeddings can be extracted from a trained model and their global, class properties (e.g., frequency, magnitude and identity) can be analyzed. We find that important information regarding the ability of a neural network to generalize to minority classes resides in the class top-K CE and FE. We show that a CNN learns a limited number of class top-K CE per category, and that their number and magnitudes vary based on whether the same class is balanced or imbalanced. This calls into question whether a CNN has learned intrinsic class features, or merely frequently occurring ones that happen to exist in the sampled class distribution. We also hypothesize that latent class diversity is as important as the number of class examples, which has important implications for re-sampling and cost-sensitive methods. These methods generally focus on rebalancing model weights, class numbers and margins; instead of diversifying class latent features through augmentation. We also demonstrate that a CNN has difficulty generalizing to test data if the magnitude of its top-K latent features do not match the training set. We use three popular image datasets and two cost-sensitive algorithms commonly employed in imbalanced learning for our experiments.

Related papers

• A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations [0.0]
  Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Yet it remains poorly understood how CNNs actually make their decisions, what the nature of their internal representations is, and how their recognition strategies differ from humans.
  arXiv  Detail & Related papers  (2022-12-12T16:40:29Z)
• What Can Be Learnt With Wide Convolutional Neural Networks? [69.55323565255631]
  We study infinitely-wide deep CNNs in the kernel regime. We prove that deep CNNs adapt to the spatial scale of the target function. We conclude by computing the generalisation error of a deep CNN trained on the output of another deep CNN.
  arXiv  Detail & Related papers  (2022-08-01T17:19:32Z)
• How explainable are adversarially-robust CNNs? [7.143109213647008]
  Three important criteria of existing convolutional neural networks (CNNs) are (1) test-set accuracy; (2) out-of-distribution accuracy; and (3) explainability. Here, we perform the first, large-scale evaluation of the relations of the three criteria using 9 feature-importance methods and 12 ImageNet-trained CNNs.
  arXiv  Detail & Related papers  (2022-05-25T20:24:19Z)
• Do Deep Networks Transfer Invariances Across Classes? [123.84237389985236]
  We show how a generative approach for learning the nuisance transformations can help transfer invariances across classes. Our results provide one explanation for why classifiers generalize poorly on unbalanced and longtailed distributions.
  arXiv  Detail & Related papers  (2022-03-18T04:38:18Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• Procrustean Training for Imbalanced Deep Learning [40.85940706868622]
  We show that a neural network tends to first under-fit the minor classes by classifying most of their data into the major classes. We propose a novel learning strategy to equalize the training progress across classes.
  arXiv  Detail & Related papers  (2021-04-05T04:44:01Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications [2.1485350418225244]
  We propose using the feature space that results from the training dataset to automatically label problematic images. The resulting semi-supervised incremental learning process allows improving the classification accuracy of new instances by 40%.
  arXiv  Detail & Related papers  (2020-11-11T12:31:48Z)
• A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers [54.996358399108566]
  We investigate the performance of the landmark general CNN classifiers, which presented top-notch results on large scale classification datasets. We compare it against state-of-the-art fine-grained classifiers. We show an extensive evaluation on six datasets to determine whether the fine-grained classifier is able to elevate the baseline in their experiments.
  arXiv  Detail & Related papers  (2020-03-24T23:49:14Z)
• Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks [52.972605601174955]
  We show a ResNet-type CNN can attain the minimax optimal error rates in important function classes. We derive approximation and estimation error rates of the aformentioned type of CNNs for the Barron and H"older classes.
  arXiv  Detail & Related papers  (2019-03-24T19:42:39Z)

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.