# Context-Aware Zero-Shot Learning for Object Recognition

arXiv: https://arxiv.org/abs/1904.12638 · HTML: https://mlsanity.com/paper/1904.12638/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2104.06601/) (2021)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baseline](https://mlsanity.com/paper/2302.07319/) (2023)
- [Zero-shot Learning with Deep Neural Networks for Object Recognition](https://mlsanity.com/paper/2102.03137/) (2021)
- [Unsupervised domain adaptation with non-stochastic missing data](https://mlsanity.com/paper/2109.09505/) (2021)
- [Context-driven Visual Object Recognition based on Knowledge Graphs](https://mlsanity.com/paper/2210.11233/) (2022)

## Abstract (arXiv)

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual appearance, are taken into account while their context, e.g. the surrounding objects in the image, is ignored. Following the intuitive principle that objects tend to be found in certain contexts but not others, we propose a new and challenging approach, context-aware ZSL, that leverages semantic representations in a new way to model the conditional likelihood of an object to appear in a given context. Finally, through extensive experiments conducted on Visual Genome, we show that contextual information can substantially improve the standard ZSL approach and is robust to unbalanced classes.