CoChat
Sign Up
Cited by 1,080Domain Adaptation and Few-Shot LearningGenerative Adversarial Networks and Image SynthesisAdvanced Neural Network Applications

Feature Generating Networks for Zero-Shot Learning

Open access
Xian, Yongqin, Lorenz, Tobias, Schiele, Bernt, Akata, Zeynep·2018·2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
DOI 10.1109/cvpr.2018.00581
Open this paper in CoChat — free accountOpen PDF

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.

Integrity signals

Registry

Crossref · 10.1109/cvpr.2018.00581

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Such methods tend to use generative adversarial network models to synthesize and reconstruct visual features of unseen classes, resulting in high accuracy classification and ensuring a balance between seen and unseen class labels.

    “Such methods tend to use GAN models to synthesize and reconstruct the visual features of the unseen classes, resulting in high accuracy classification and ensuring a balance between seen and unseen class labels [136, 137].”

    From A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2022) · cites this paper as [136]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Xian, Y., Lorenz, T., Schiele, B., & Akata, Z.
Affiliations
Max Planck Institute for Informatics (DE)
ORCID
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
5542-5551
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2018.00581
OpenAlex
W2963960318
Cited by
1,080
References
40
Citations by year
2026: 49 · 2025: 102 · 2024: 152 · 2023: 139 · 2022: 164 · 2021: 201 · 2020: 159 · 2019: 95 · 2018: 18 · 2012: 1
FWCI
48.27
Type
conference paper
Language
en
Open access
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • UvA-DARE (University of Amsterdam) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Max Planck Digital Library (submittedVersion)
  • MPG.PuRe (Max Planck Society) (submittedVersion)
  • Data Archiving and Networked Services (DANS) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
zero-shot learning, generalized zero-shot learning, feature construction, generative adversarial networks, Wasserstein GAN, imbalanced training data, softmax classification

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review