GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning

by   Zhi Chen, et al.

Generalized Zero-Shot Learning (GZSL) aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. However, due to the generation shifts, the synthesized samples by most existing methods may drift from the real distribution of the unseen data. To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation. Specifically, we discover and address three potential problems that trigger the generation shifts, i.e., semantic inconsistency, variance collapse, and structure disorder. First, to enhance the reflection of the semantic information in the generated samples, we explicitly embed the semantic information into the transformation in each conditional affine coupling layer. Second, to recover the intrinsic variance of the real unseen features, we introduce a boundary sample mining strategy with entropy maximization to discover more difficult visual variants of semantic prototypes and hereby adjust the decision boundary of the classifiers. Third, a relative positioning strategy is proposed to revise the attribute embeddings, guiding them to fully preserve the inter-class geometric structure and further avoid structure disorder in the semantic space. Extensive experimental results on four GZSL benchmark datasets demonstrate that GSMFlow achieves the state-of-the-art performance on GZSL.


page 1

page 4

page 6

page 10


Mitigating Generation Shifts for Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic...

Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize novel classes by transferring...

Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning

Compared to conventional zero-shot learning (ZSL) where recognising unse...

Semantic Disentangling Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) aims to recognize images from both...

Zero-Shot Learning by Harnessing Adversarial Samples

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizin...

Generalizing over Long Tail Concepts for Medical Term Normalization

Medical term normalization consists in mapping a piece of text to a larg...

Invertible Zero-Shot Recognition Flows

Deep generative models have been successfully applied to Zero-Shot Learn...

Please sign up or login with your details

Forgot password? Click here to reset