Bias-Eliminated Semantic Refinement for Any-Shot Learning

TL;DR

This paper introduces SRWGAN, a novel semantic refinement model that eliminates bias in semantic descriptions, significantly improving visual feature generation for zero-shot, generalized zero-shot, and few-shot learning across multiple datasets.

Contribution

The paper proposes a new semantic refinement Wasserstein GAN with multihead representation and hierarchical alignment for bias-free feature generation in any-shot learning.

Findings

Achieved 70.2% harmonic accuracy on CUB dataset in GZSL.

Achieved 82.2% harmonic accuracy on FLO dataset in GZSL.

Outperformed existing methods with state-of-the-art results on six benchmark datasets.

Abstract

When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects. However, semantic descriptions are usually obtained in an external paradigm, such as manual annotation, resulting in weak consistency between descriptions and visual features. In this paper, we refine the coarse-grained semantic description for any-shot learning tasks, ie, zero-shot learning (ZSL), generalized zero-shot learning (GZSL), and few-shot learning (FSL). A new model, namely, the semantic refinement Wasserstein generative adversarial network (SRWGAN) model, is designed with the proposed multihead representation and hierarchical alignment techniques. Unlike conventional methods, semantic refinement is performed with the aim of identifying a bias-eliminated condition for disjoint-class feature generation and is applicable in both inductive and transductive settings. We extensively evaluate model performance on six benchmark datasets and observe state-of-the-art results for any-shot learning; eg, we obtain 70.2% harmonic accuracy for the Caltech UCSD Birds (CUB) dataset and 82.2% harmonic accuracy for the Oxford Flowers (FLO) dataset in the standard GZSL setting. Various visualizations are also provided to show the bias-eliminated generation of SRWGAN. Our code is available.