PulseAugur
中
实时 22:17:37

Hierarchy-Aware Cross-Entropy improves image classification accuracy

作者 PulseAugur 编辑部 · [2 个来源] ·

Researchers have introduced Hierarchy-Aware Cross-Entropy (HACE), a novel loss function designed to improve image classification by accounting for semantic relationships between classes. Unlike standard cross-entropy, HACE incorporates a class hierarchy to better handle misclassifications. The method involves aggregating prediction probabilities upward and applying ancestral label smoothing to the ground truth. Evaluations on datasets like CIFAR-100 demonstrated that HACE can enhance accuracy, particularly when used with frozen DINOv2-Large features. AI

影响 Introduces a new loss function that could improve the accuracy of image classification models by better leveraging class hierarchies.

排序理由 Academic paper introducing a new method for image classification.

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Hierarchy-Aware Cross-Entropy improves image classification accuracy

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · April Chan, Davide D'Ascenzo, Sebastiano Cultrera di Montesano ·

    When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy

    arXiv:2605.06274v1 Announce Type: new Abstract: Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-A…

  2. arXiv cs.CV TIER_1 English(EN) · Sebastiano Cultrera di Montesano ·

    When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy

    Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-Aware Cross-Entropy (HACE), a drop-in replacement…

相关实体

相关话题