# Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

Source: [Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings](<https://www.sota2.com/research/paper/68fa68c21e209131cea1e1a1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:44:52.991Z

Authors: Karan Sikka, Jihua Huang, Andrew Silberfarb, Prateeth Nayak, Luke Rohrer, Pritish Sahu, John Byrnes, Ajay Divakaran, Richard Rohwer

Published: 2020-11-21T22:58:38.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2011.10889>)

[PDF](<https://arxiv.org/pdf/2011.10889.pdf>)