# Zero-Shot Learning with Sparse Attribute Propagation

## TL;DR

This paper introduces a new zero-shot learning setting with limited annotated images per class and proposes a sparse attribute propagation method to enhance attribute annotation transfer, improving ZSL and social image annotation performance.

## Contribution

The paper presents a novel inductive ZSL model called sparse attribute propagation (SAP) that addresses attribute sparsity with sparse coding and bidirectional projections, extending ZSL to more realistic scenarios.

## Key findings

- SAP improves ZSL accuracy significantly.
- Augmenting datasets with web images enhances performance.
- SAP is effective for social image annotation.

## Abstract

Zero-shot learning (ZSL) aims to recognize a set of unseen classes without any training images. The standard approach to ZSL requires a set of training images annotated with seen class labels and a semantic descriptor for seen/unseen classes (attribute vector is the most widely used). Class label/attribute annotation is expensive; it thus severely limits the scalability of ZSL. In this paper, we define a new ZSL setting where only a few annotated images are collected from each seen class. This is clearly more challenging yet more realistic than the conventional ZSL setting. To overcome the resultant image-level attribute sparsity, we propose a novel inductive ZSL model termed sparse attribute propagation (SAP) by propagating attribute annotations to more unannotated images using sparse coding. This is followed by learning bidirectional projections between features and attributes for ZSL. An efficient solver is provided, together with rigorous theoretic algorithm analysis. With our SAP, we show that a ZSL training dataset can now be augmented by the abundant web images returned by image search engine, to further improve the model performance. Moreover, the general applicability of SAP is demonstrated on solving the social image annotation (SIA) problem. Extensive experiments show that our model achieves superior performance on both ZSL and SIA.