Improved Feature Generating Framework for Transductive Zero-shot Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Zihan, Ru, Xinyuan, Chen, Shiming, Jin, Yaochu, Huang, Kaizhu, Jin, Xiaobo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915078178078720
author Ye, Zihan
Ru, Xinyuan
Chen, Shiming
Jin, Yaochu
Huang, Kaizhu
Jin, Xiaobo
author_facet Ye, Zihan
Ru, Xinyuan
Chen, Shiming
Jin, Yaochu
Huang, Kaizhu
Jin, Xiaobo
contents Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes within the scope of Zero-shot Learning (ZSL). This paper delves into the pivotal influence of unseen class priors within the framework of transductive ZSL (TZSL) and illuminates the finding that even a marginal prior bias can result in substantial accuracy declines. Our extensive analysis uncovers that this inefficacy fundamentally stems from the utilization of an unconditional unseen discriminator - a core component in existing TZSL. We further establish that the detrimental effects of this component are inevitable unless the generator perfectly fits class-specific distributions. Building on these insights, we introduce our Improved Feature Generation Framework, termed I-VAEGAN, which incorporates two novel components: Pseudo-conditional Feature Adversarial (PFA) learning and Variational Embedding Regression (VER). PFA circumvents the need for prior estimation by explicitly injecting the predicted semantics as pseudo conditions for unseen classes premised by precise semantic regression. Meanwhile, VER utilizes reconstructive pre-training to learn class statistics, obtaining better semantic regression. Our I-VAEGAN achieves state-of-the-art TZSL accuracy across various benchmarks and priors. Our code would be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18282
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improved Feature Generating Framework for Transductive Zero-shot Learning
Ye, Zihan
Ru, Xinyuan
Chen, Shiming
Jin, Yaochu
Huang, Kaizhu
Jin, Xiaobo
Computer Vision and Pattern Recognition
Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes within the scope of Zero-shot Learning (ZSL). This paper delves into the pivotal influence of unseen class priors within the framework of transductive ZSL (TZSL) and illuminates the finding that even a marginal prior bias can result in substantial accuracy declines. Our extensive analysis uncovers that this inefficacy fundamentally stems from the utilization of an unconditional unseen discriminator - a core component in existing TZSL. We further establish that the detrimental effects of this component are inevitable unless the generator perfectly fits class-specific distributions. Building on these insights, we introduce our Improved Feature Generation Framework, termed I-VAEGAN, which incorporates two novel components: Pseudo-conditional Feature Adversarial (PFA) learning and Variational Embedding Regression (VER). PFA circumvents the need for prior estimation by explicitly injecting the predicted semantics as pseudo conditions for unseen classes premised by precise semantic regression. Meanwhile, VER utilizes reconstructive pre-training to learn class statistics, obtaining better semantic regression. Our I-VAEGAN achieves state-of-the-art TZSL accuracy across various benchmarks and priors. Our code would be released upon acceptance.
title Improved Feature Generating Framework for Transductive Zero-shot Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.18282