Invertible Zero-Shot Recognition Flows

by   Yuming Shen, et al.

Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently. However, the underlying drawbacks of GANs and VAEs (e.g., the hardness of training with ZSL-oriented regularizers and the limited generation quality) hinder the existing generative ZSL models from fully bypassing the seen-unseen bias. To tackle the above limitations, for the first time, this work incorporates a new family of generative models (i.e., flow-based models) into ZSL. The proposed Invertible Zero-shot Flow (IZF) learns factorized data embeddings (i.e., the semantic factors and the non-semantic ones) with the forward pass of an invertible flow network, while the reverse pass generates data samples. This procedure theoretically extends conventional generative flows to a factorized conditional scheme. To explicitly solve the bias problem, our model enlarges the seen-unseen distributional discrepancy based on negative sample-based distance measurement. Notably, IZF works flexibly with either a naive Bayesian classifier or a held-out trainable one for zero-shot recognition. Experiments on widely-adopted ZSL benchmarks demonstrate the significant performance gain of IZF over existing methods, in both classic and generalized settings.


page 1

page 2

page 3

page 4


Zero-Shot Logit Adjustment

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses ch...

FREE: Feature Refinement for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) has achieved significant progress,...

Domain segmentation and adjustment for generalized zero-shot learning

In the generalized zero-shot learning, synthesizing unseen data with gen...

A Meta-Learning Framework for Generalized Zero-Shot Learning

Learning to classify unseen class samples at test time is popularly refe...

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

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

Towards the Semantic Weak Generalization Problem in Generative Zero-Shot Learning: Ante-hoc and Post-hoc

In this paper, we present a simple and effective strategy lowering the p...