Knowledge Distillation Classifier Generation Network for Zero-Shot Learning

Yunlong Yu, Bin Li, Zhong Ji, Jungong Han, Zhongfei Zhang

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)
62 Downloads (Pure)

Abstract

In this article, we present a conceptually simple but effective framework called knowledge distillation classifier generation network (KDCGN) for zero-shot learning (ZSL), where the learning agent requires recognizing unseen classes that have no visual data for training. Different from the existing generative approaches that synthesize visual features for unseen classifiers' learning, the proposed framework directly generates classifiers for unseen classes conditioned on the corresponding class-level semantics. To ensure the generated classifiers to be discriminative to the visual features, we borrow the knowledge distillation idea to both supervise the classifier generation and distill the knowledge with, respectively, the visual classifiers and soft targets trained from a traditional classification network. Under this framework, we develop two, respectively, strategies, i.e., class augmentation and semantics guidance, to facilitate the supervision process from the perspectives of improving visual classifiers. Specifically, the class augmentation strategy incorporates some additional categories to train the visual classifiers, which regularizes the visual classifier weights to be compact, under supervision of which the generated classifiers will be more discriminative. The semantics-guidance strategy encodes the class semantics into the visual classifiers, which would facilitate the supervision process by minimizing the differences between the generated and the real-visual classifiers. To evaluate the effectiveness of the proposed framework, we have conducted extensive experiments on five datasets in image classification, i.e., AwA1, AwA2, CUB, FLO, and APY. Experimental results show that the proposed approach performs best in the traditional ZSL task and achieves a significant performance improvement on four out of the five datasets in the generalized ZSL task.

Original languageEnglish
Pages (from-to)3183-3194
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume34
Issue number6
Early online date29 Sept 2021
DOIs
Publication statusPublished - 01 Jun 2023

Keywords

  • Class-augmentation
  • classifier generation
  • knowledge distillation
  • Knowledge engineering
  • Learning systems
  • Prototypes
  • Semantics
  • semantics-guidance (SG)
  • Task analysis
  • Training
  • Visualization
  • zero-shot learning (ZSL).
  • zero-shot learning (ZSL)

Fingerprint

Dive into the research topics of 'Knowledge Distillation Classifier Generation Network for Zero-Shot Learning'. Together they form a unique fingerprint.

Cite this