# Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning

arXiv: https://arxiv.org/abs/1705.01734 · HTML: https://mlsanity.com/paper/1705.01734/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2017.

## Built on by (most cited first, 12 of 12)

- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [Zero-shot Natural Language Video Localization](https://mlsanity.com/paper/2110.00428/) (2021)
- [Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding](https://mlsanity.com/paper/2203.08481/) (2022)
- [Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2305.14335/) (2023)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2305.13173/) (2023)
- [Explaining CLIP Zero-shot Predictions Through Concepts](https://mlsanity.com/paper/2603.28211/) (2026)
- [SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization](https://mlsanity.com/paper/2202.13100/) (2022)
- [Caption Generation on Scenes with Seen and Unseen Object Categories](https://mlsanity.com/paper/2108.06165/) (2021)
- [Feature Embedding by Template Matching as a ResNet Block](https://mlsanity.com/paper/2210.00992/) (2022)
- [Generalized Sum Pooling for Metric Learning](https://mlsanity.com/paper/2308.09228/) (2023)
- [Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning](https://mlsanity.com/paper/2309.06987/) (2023)

## Abstract (arXiv)

We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively learn a word representation such that the similarities between class and combination of attribute names fall in line with the visual similarity. Contrary to the traditional zero-shot learning approaches that are built upon attribute presence, our approach bypasses the laborious attribute-class relation annotations for unseen classes. In addition, our proposed approach renders text-only training possible, hence, the training can be augmented without the need to collect additional image data. The experimental results show that our method yields state-of-the-art results for unsupervised ZSL in three benchmark datasets.