Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

TL;DR

This paper enhances zero-shot learning by integrating common-sense knowledge into visual-semantic embeddings through a neuro-symbolic loss, leading to significant performance improvements across multiple datasets.

Contribution

It introduces a novel neuro-symbolic loss that incorporates common-sense rules and class relationships into ZSL models, improving their generalization.

Findings

Achieved 11.5% improvement on AWA2 dataset

Gained 5.5% on CUB dataset

Improved 11.6% on Kinetics dataset

Abstract

We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that regularize visual-semantic embedding. CSNL forces visual features in the VSE to obey common-sense rules relating to hypernyms and attributes. We introduce two key novelties for improved learning: (1) enforcement of rules for a group instead of a single concept to take into account class-wise relationships, and (2) confidence margins inside logical operators that enable implicit curriculum learning and prevent premature overfitting. We evaluate the advantages of incorporating each knowledge source and show consistent gains over prior state-of-art methods in both conventional and generalized ZSL e.g. 11.5%, 5.5%, and 11.6% improvements on AWA2, CUB, and Kinetics respectively.