SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning

TL;DR

SDM-Net introduces a simple neural network architecture for generalized zero-shot learning that leverages similarity-based soft-labeling, achieving consistent state-of-the-art results across multiple benchmark datasets.

Contribution

The paper presents a novel zero-shot learning model that uses similarity-based soft-labeling within a standard neural network framework, simplifying the approach and improving performance.

Findings

Achieves significant improvements over state-of-the-art methods.

Performs well on four benchmark datasets: AwA, aPY, SUN, and CUB.

Effective in both generalized and standard ZSL settings.

Abstract

Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information (or description) about seen and unseen classes, often in the form of physically realizable or descriptive attributes. Lack of any single training example from a set of classes prohibits use of standard classification techniques and losses, including the popular crossentropy loss. Currently, state-of-the-art approaches encode the prior class information into dense vectors and optimize some distance between the learned projections of the input vector and the corresponding class vector (collectively known as embedding models). In this paper, we propose a novel architecture of casting zero-shot learning as a standard neural-network with crossentropy loss. During training our approach performs soft-labeling by combining the observed training data for the seen classes with the similarity information from the attributes for which we have no training data or unseen classes. To the best of our knowledge, such similarity based soft-labeling is not explored in the field of deep learning. We evaluate the proposed model on the four benchmark datasets for zero-shot learning, AwA, aPY, SUN and CUB datasets, and show that our model achieves significant improvement over the state-of-the-art methods in Generalized-ZSL and ZSL settings on all of these datasets consistently.