Feature Generating Networks for Zero-Shot Learning

2017/12/04 by Yongqin Xian, Tobias Lorenz, Xian, Yongqin +5 · 18 citations
Computer Science · Engineering · Medicine · #Artificial intelligence #COVID-19 diagnosis using AI #Class (philosophy) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Deep learning #Discriminative model #Domain Adaptation and Few-Shot Learning #Embedding #Engineering #FOS: Computer and information sciences #Feature (linguistics) #Generative grammar #Machine learning #Pattern recognition (psychology) #Semantic feature #Shot (pellet) #Softmax function #Task (project management) #Zero (linguistics) #cs.CV

paper · pdf · doi:10.48550/arxiv.1712.00981

published in arXiv (Cornell University) (Cornell University) · 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

openalex publication_date 2017/12/04 · arxiv created 2018/04/12 · arxiv updated 2018/04/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning task. To circumvent the need for labeled examples of unseen classes, we propose a novel generative adversarial network (GAN) that synthesizes CNN features conditioned on class-level semantic information, offering a shortcut directly from a semantic descriptor of a class to a class-conditional feature distribution. Our proposed approach, pairing a Wasserstein GAN with a classification loss, is able to generate sufficiently discriminative CNN features to train softmax classifiers or any multimodal embedding method. Our experimental results demonstrate a significant boost in accuracy over the state of the art on five challenging datasets -- CUB, FLO, SUN, AWA and ImageNet -- in both the zero-shot learning and generalized zero-shot learning settings.

Cited by

• Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
• Fine-Grained Zero-Shot Learning with Attribute-Centric Representations
• Distributed Zero-Shot Learning for Visual Recognition
• Multi-Granularity Mutual Refinement Network for Zero-Shot Learning
• Toward a More Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data
• Class Similarity-Based Multimodal Classification under Heterogeneous Category Sets
• Prototype-Guided Curriculum Learning for Zero-Shot Learning
• Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
• Deep Mixture of Experts via Shallow Embedding
• A Conditional Probability Framework for Compositional Zero-shot Learning
• Is Visual in-Context Learning for Compositional Medical Tasks within Reach?
• Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model
• Few-Shot Inspired Generative Zero-Shot Learning
• Interpretable Zero-shot Learning with Infinite Class Concepts
• Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning
• GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition
• GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder

Related

• SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
• f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
• Structure-Aware Feature Generation for Zero-Shot Learning
• Leveraging the Invariant Side of Generative Zero-Shot Learning
• Generative Dual Adversarial Network for Generalized Zero-shot Learning