Learning Hierarchy Aware Features for Reducing Mistake Severity

• URL: http://arxiv.org/abs/2207.12646v1
• Date: Tue, 26 Jul 2022 04:24:47 GMT
• Title: Learning Hierarchy Aware Features for Reducing Mistake Severity
• Authors: Ashima Garg, Depanshu Sani, Saket Anand
• Abstract summary: We propose a novel approach for learning hierarchy aware features (HAF) HAF is a training time approach that improves the mistakes while maintaining top-1 error, thereby, addressing the problem of cross-entropy loss that treats all mistakes as equal. We evaluate HAF on three hierarchical datasets and achieve state-of-the-art results on the iNaturalist-19 and CIFAR-100 datasets.
• Score: 3.704832909610283
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label hierarchies are often available apriori as part of biological taxonomy or language datasets WordNet. Several works exploit these to learn hierarchy aware features in order to improve the classifier to make semantically meaningful mistakes while maintaining or reducing the overall error. In this paper, we propose a novel approach for learning Hierarchy Aware Features (HAF) that leverages classifiers at each level of the hierarchy that are constrained to generate predictions consistent with the label hierarchy. The classifiers are trained by minimizing a Jensen-Shannon Divergence with target soft labels obtained from the fine-grained classifiers. Additionally, we employ a simple geometric loss that constrains the feature space geometry to capture the semantic structure of the label space. HAF is a training time approach that improves the mistakes while maintaining top-1 error, thereby, addressing the problem of cross-entropy loss that treats all mistakes as equal. We evaluate HAF on three hierarchical datasets and achieve state-of-the-art results on the iNaturalist-19 and CIFAR-100 datasets. The source code is available at https://github.com/07Agarg/HAF

Related papers

• Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity [0.0]
  We propose to fix the linear classifier of a deep neural network to a Hierarchy-Aware Frame (HAFrame) We demonstrate that our approach reduces the mistake severity of the model's predictions while maintaining its top-1 accuracy on several datasets.
  arXiv  Detail & Related papers  (2023-03-10T03:44:01Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets [24.868024094095983]
  Open vocabulary models (e.g. CLIP) have shown strong performance on zero-shot classification. We propose Classification with Hierarchical Label Sets (or CHiLS) for datasets with implicit semantic hierarchies. CHiLS is simple to implement within existing zero-shot pipelines and requires no additional training cost.
  arXiv  Detail & Related papers  (2023-02-06T03:59:15Z)
• Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework [75.79736930414715]
  We present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint.
  arXiv  Detail & Related papers  (2022-04-27T21:41:44Z)
• 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)
• Rank-based loss for learning hierarchical representations [7.421724671710886]
  In machine learning, the family of methods that use the 'extra' information is called hierarchical classification. Here we focus on how to integrate the hierarchical information of a problem to learn embeddings representative of the hierarchical relationships. We show that rank based loss is suitable to learn hierarchical representations of the data.
  arXiv  Detail & Related papers  (2021-10-11T10:32:45Z)
• Learning by Minimizing the Sum of Ranked Range [58.24935359348289]
  We introduce the sum of ranked range (SoRR) as a general approach to form learning objectives. A ranked range is a consecutive sequence of sorted values of a set of real numbers. We explore two applications in machine learning of the minimization of the SoRR framework, namely the AoRR aggregate loss for binary classification and the TKML individual loss for multi-label/multi-class classification.
  arXiv  Detail & Related papers  (2020-10-05T01:58:32Z)
• Exploring the Hierarchy in Relation Labels for Scene Graph Generation [75.88758055269948]
  The proposed method can improve several state-of-the-art baselines by a large margin (up to $33%$ relative gain) in terms of Recall@50. Experiments show that the proposed simple yet effective method can improve several state-of-the-art baselines by a large margin.
  arXiv  Detail & Related papers  (2020-09-12T17:36:53Z)
• Hierarchical Class-Based Curriculum Loss [18.941207332233805]
  Most real world data have dependencies between labels, which can be captured by using a hierarchy. We propose a loss function, hierarchical curriculum loss, with two properties: (i) satisfy hierarchical constraints present in the label space, and (ii) provide non-uniform weights to labels based on their levels in the hierarchy.
  arXiv  Detail & Related papers  (2020-06-05T18:48:57Z)
• Self-Learning with Rectification Strategy for Human Parsing [73.06197841003048]
  We propose a trainable graph reasoning method to correct two typical errors in the pseudo-labels. The reconstructed features have a stronger ability to represent the topology structure of the human body. Our method outperforms other state-of-the-art methods in supervised human parsing tasks.
  arXiv  Detail & Related papers  (2020-04-17T03:51:30Z)

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.