Bias-Eliminated Semantic Refinement for Any-Shot Learning
This work addresses the challenge of improving few-shot and zero-shot learning for computer vision applications by eliminating bias in semantic descriptions, though it appears incremental as it builds on existing generative adversarial network methods.
The paper tackles the problem of weak consistency between semantic descriptions and visual features in any-shot learning by refining coarse-grained semantic descriptions, achieving state-of-the-art results such as 70.2% harmonic accuracy on the CUB dataset and 82.2% on the FLO dataset in generalized zero-shot learning.
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.