# Simple and effective localized attribute representations for zero-shot learning

arXiv: https://arxiv.org/abs/2006.05938 · HTML: https://mlsanity.com/paper/2006.05938/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

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

- [Continual learning in cross-modal retrieval](https://mlsanity.com/paper/2104.06806/) (2021)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)
- [Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations](https://mlsanity.com/paper/2207.03824/) (2022)
- [Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning](https://mlsanity.com/paper/2112.00410/) (2021)
- [An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning](https://mlsanity.com/paper/2111.02139/) (2021)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2404.08761/) (2024)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features together with fine-tuning the feature extractor to obtain discriminative and transferable features. However, these methods require complex attention or part detection modules to perform explicit localization in the visual space. In contrast, in this paper we propose localizing representations in the semantic/attribute space, with a simple but effective pipeline where localization is implicit. Focusing on attribute representations, we show that our method obtains state-of-the-art performance on CUB and SUN datasets, and also achieves competitive results on AWA2 dataset, outperforming generally more complex methods with explicit localization in the visual space. Our method can be implemented easily, which can be used as a new baseline for zero shot-learning. In addition, our localized representations are highly interpretable as attribute-specific heatmaps.