# Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition

arXiv: https://arxiv.org/abs/1807.09123 · HTML: https://mlsanity.com/paper/1807.09123/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2018.

## Built on by (most cited first, 14 of 14)

- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://mlsanity.com/paper/2212.00244/) (2022)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2111.15656/) (2021)
- [Disentangling Semantic-to-visual Confusion for Zero-shot Learning](https://mlsanity.com/paper/2106.08605/) (2021)
- [Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations](https://mlsanity.com/paper/2207.03824/) (2022)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation](https://mlsanity.com/paper/2112.12573/) (2021)
- [Semantically Grounded Visual Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2201.00577/) (2022)
- [Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2503.23030/) (2025)
- [Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2104.01832/) (2021)
- ["Zero-Shot" Point Cloud Upsampling](https://mlsanity.com/paper/2106.13765/) (2021)
- [Learning Compositional Representations for Effective Low-Shot Generalization](https://mlsanity.com/paper/2204.08090/) (2022)
- [Zero-sample surface defect detection and classification based on semantic feedback neural network](https://mlsanity.com/paper/2106.07959/) (2021)
- [CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension](https://mlsanity.com/paper/2608.13751/) (2026)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on learning visual-semantic embeddings to transfer knowledge from the auxiliary datasets to the novel classes. However, few works study whether the semantic information is discriminative or not for the recognition task. To tackle such problem, we propose a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, where the discriminative information lying in the visual space is utilized to improve the less discriminative semantic space. Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes. Extensive experiments on four benchmark datasets show the effectiveness of the proposed approach.