Multi-Label Knowledge Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Penghui, Xie, Ming-Kun, Zong, Chen-Chen, Feng, Lei, Niu, Gang, Sugiyama, Masashi, Huang, Sheng-Jun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916766636048384
author Yang, Penghui
Xie, Ming-Kun
Zong, Chen-Chen
Feng, Lei
Niu, Gang
Sugiyama, Masashi
Huang, Sheng-Jun
author_facet Yang, Penghui
Xie, Ming-Kun
Zong, Chen-Chen
Feng, Lei
Niu, Gang
Sugiyama, Masashi
Huang, Sheng-Jun
contents Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning. However, these methods can hardly be extended to the multi-label learning scenario, where each instance is associated with multiple semantic labels, because the prediction probabilities do not sum to one and feature maps of the whole example may ignore minor classes in such a scenario. In this paper, we propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems; on the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings. Experimental results on multiple benchmark datasets validate that the proposed method can avoid knowledge counteraction among labels, thus achieving superior performance against diverse comparing methods. Our code is available at: https://github.com/penghui-yang/L2D
format Preprint
id arxiv_https___arxiv_org_abs_2308_06453
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-Label Knowledge Distillation
Yang, Penghui
Xie, Ming-Kun
Zong, Chen-Chen
Feng, Lei
Niu, Gang
Sugiyama, Masashi
Huang, Sheng-Jun
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning. However, these methods can hardly be extended to the multi-label learning scenario, where each instance is associated with multiple semantic labels, because the prediction probabilities do not sum to one and feature maps of the whole example may ignore minor classes in such a scenario. In this paper, we propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems; on the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings. Experimental results on multiple benchmark datasets validate that the proposed method can avoid knowledge counteraction among labels, thus achieving superior performance against diverse comparing methods. Our code is available at: https://github.com/penghui-yang/L2D
title Multi-Label Knowledge Distillation
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.06453