Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation

2021-12-23 · Xiaojie Zhao, Yuming Shen, Shidong Wang, Haofeng Zhang

The recent advance in deep generative models outlines a promising perspective in the realm of Zero-Shot Learning (ZSL). Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features. After generating unseen samples, this family of approaches effectively transforms the ZSL problem into a supervised classification scheme. However, the existing models use a single semantic attribute, which contains the complete attribute information of the category. The generated data also carry the complete attribute information, but in reality, visual samples usually have limited attributes. Therefore, the generated data from attribute could have incomplete semantics. Based on this fact, we propose a novel framework to boost ZSL by synthesizing diverse features. This method uses augmented semantic attributes to train the generative model, so as to simulate the real distribution of visual features. We evaluate the proposed model on four benchmark datasets, observing significant performance improvement against the state-of-the-art.

📄 PDF Abstract BibTeX arXiv:2112.12573

Code (1)

njzxj/sdfa 공식 구현 pytorch

Tasks

AttributeZero-Shot Learning

Generative Multi-Label Zero-Shot Learning

2021-01-27 · Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan 외

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized varia…

Attribute Generative Adversarial Network image-classification Image Classification+3

Domain segmentation and adjustment for generalized zero-shot learning

2020-02-01 · Xinsheng Wang, Shanmin Pang, Jihua Zhu

In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes. However, this method requ…

Generalized Zero-Shot Learning Zero-Shot Learning

RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions

2024-12-31 · Wanlong Liu, Junying Chen, Ke Ji, Li Zhou 외

Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover li…

Diversity RAG Retrieval Retrieval-augmented Generation

D3G: Diverse Demographic Data Generation Increases Zero-Shot Image Classification Accuracy within Multimodal Models

2025-12-10 · Javon Hickmon arxiv

Image classification is a task essential for machine perception to achieve human-level image understanding. Multimodal models such as CLIP have been able to perform well on this task by learning semantic similarities acr…

Fine-Grained Image Classification Zero-Shot Image Classification

Zero-Shot Text-to-Speech for Vietnamese

2025-06-02 · Thi Vu, Linh The Nguyen, Dat Quoc Nguyen

This paper introduces PhoAudiobook, a newly curated dataset comprising 941 hours of high-quality audio for Vietnamese text-to-speech. Using PhoAudiobook, we conduct experiments on three leading zero-shot TTS models: VALL…

text-to-speech Text to Speech