Mitigating Generation Shifts for Generalized Zero-Shot Learning

TL;DR

This paper introduces GSMFlow, a novel flow-based model that mitigates generation shifts in generalized zero-shot learning by addressing semantic inconsistency, variance decay, and structural permutation, leading to improved recognition accuracy.

Contribution

The paper proposes GSMFlow, a flow-based framework with strategies to reduce generation shifts in GZSL, enhancing unseen data synthesis and classification performance.

Findings

Achieves state-of-the-art results in GZSL tasks.

Effectively addresses semantic inconsistency and variance decay.

Improves the quality of generated unseen class samples.

Abstract

Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. It is natural to derive generative models and hallucinate training samples for unseen classes based on the knowledge learned from the seen samples. However, most of these models suffer from the `generation shifts', where the synthesized samples may drift from the real distribution of unseen data. In this paper, we conduct an in-depth analysis on this issue and propose a novel Generation Shifts Mitigating Flow (GSMFlow) framework, which is comprised of multiple conditional affine coupling layers for learning unseen data synthesis efficiently and effectively. In particular, we identify three potential problems that trigger the generation shifts, i.e., semantic inconsistency, variance decay, and structural permutation and address them respectively. First, to reinforce the correlations between the generated samples and the respective attributes, we explicitly embed the semantic information into the transformations in each of the coupling layers. Second, to recover the intrinsic variance of the synthesized unseen features, we introduce a visual perturbation strategy to diversify the intra-class variance of generated data and hereby help adjust the decision boundary of the classifier. Third, to avoid structural permutation in the semantic space, we propose a relative positioning strategy to manipulate the attribute embeddings, guiding which to fully preserve the inter-class geometric structure. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings. Our code is available at: https://github.com/uqzhichen/GSMFlow