Contrastive Embedding for Generalized Zero-Shot Learning

By Zongyan Han, Zhenyong Fu, Shuo Chen, Jian Yang. 2021

270 citations recorded by the source corpus.

Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Recent feature generation methods learn a generative model that can synthesize the missing visual features of unseen classes to mitigate the data-imbalance problem in GZSL. However, the original visual feature space is suboptimal for GZSL classification since it lacks discriminative information. To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework. The hybrid GZSL approach maps both the real and the synthetic samples produced by the generation model into an embedding space, where we perform the final GZSL classification. Specifically, we propose a contrastive embedding (CE) for our hybrid GZSL framework. The proposed contrastive embedding can leverage not only the class-wise supervision but also the instance-wise supervision, where the latter is usually neglected by existing GZSL researches. We evaluate our proposed hybrid GZSL framework with contrastive embedding, named CE-GZSL, on five benchmark datasets. The results show that our CEGZSL method can outperform the state-of-the-arts by a significant margin on three datasets. Our codes are available on https://github.com/Hanzy1996/CE-GZSL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lanqing Hong
2. Zhenguo Li
3. Shipeng Yan
4. Xuming He
5. Hang Xu
6. Jianhua Han
7. Tinne Tuytelaars
8. Han-Jia Ye

In Computer Vision and Pattern Recognition

1. Zhenguo Li
2. Lanqing Hong
3. Hang Xu
4. Shipeng Yan
5. Xuming He
6. Luc Van Gool
7. Dacheng Tao
8. Alan L. Yuille

In Ocean Engineering

1. Tinne Tuytelaars
2. Xuming He

Citations in the corpus

• Generative Negative Text Replay for Continual Vision-Language Pretraining (2022, background): “including zero-shot image classification and image-text retrieval [19].”