# Multi-Cue Zero-Shot Learning with Strong Supervision

arXiv: https://arxiv.org/abs/1603.08754 · HTML: https://mlsanity.com/paper/1603.08754/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2016.

## Built on by (most cited first, 22 of 22)

- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [Semantic Diversity Learning for Zero-Shot Multi-label Classification](https://mlsanity.com/paper/2105.05926/) (2021)
- [Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention](https://mlsanity.com/paper/2203.03483/) (2022)
- [Learning Robust Visual-semantic Mapping for Zero-shot Learning](https://mlsanity.com/paper/2104.05668/) (2021)
- [Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects](https://mlsanity.com/paper/2401.17766/) (2024)
- [Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.03292/) (2021)
- [GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2309.00923/) (2023)
- [CIZSL++: Creativity Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2101.00173/) (2021)
- [BELT:Bootstrapping Electroencephalography-to-Language Decoding and Zero-Shot Sentiment Classification by Natural Language Supervision](https://mlsanity.com/paper/2309.12056/) (2023)
- [Recognize Any Regions](https://mlsanity.com/paper/2311.01373/) (2023)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning](https://mlsanity.com/paper/2111.02139/) (2021)
- [Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection](https://mlsanity.com/paper/2402.09242/) (2024)
- [Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2408.12253/) (2024)
- [Learning by Asking Questions for Knowledge-based Novel Object Recognition](https://mlsanity.com/paper/2210.05879/) (2022)
- [Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification](https://mlsanity.com/paper/2102.13322/) (2021)
- [Zero-Shot Learning Based on Knowledge Sharing](https://mlsanity.com/paper/2102.13326/) (2021)
- [Object-Level Targeted Selection via Deep Template Matching](https://mlsanity.com/paper/2207.01778/) (2022)
- [Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning](https://mlsanity.com/paper/2309.06987/) (2023)
- [Memory-Modular Classification: Learning to Generalize with Memory Replacement](https://mlsanity.com/paper/2504.06021/) (2025)
- [Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities](https://mlsanity.com/paper/2512.18651/) (2025)

## Abstract (arXiv)

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form of auxiliary information describing the new classes. Ultimately, this may allow to use textbook knowledge that humans employ to learn about new classes by transferring knowledge from classes they know well. The most successful zero-shot learning approaches currently require a particular type of auxiliary information -- namely attribute annotations performed by humans -- that is not readily available for most classes. Our goal is to circumvent this bottleneck by substituting such annotations by extracting multiple pieces of information from multiple unstructured text sources readily available on the web. To compensate for the weaker form of auxiliary information, we incorporate stronger supervision in the form of semantic part annotations on the classes from which we transfer knowledge. We achieve our goal by a joint embedding framework that maps multiple text parts as well as multiple semantic parts into a common space. Our results consistently and significantly improve on the state-of-the-art in zero-short recognition and retrieval.