Papers › Feature Generating Networks for Zero-Shot Learning

Feature Generating Networks for Zero-Shot Learning

4 Dec 2017CVPR 2018 6arXiv:1712.00981archive 2025-07-28

Yongqin Xian, Tobias Lorenz, Bernt Schiele, Zeynep Akata

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Abhipanda4/Feature-Generating-Networks mentioned on GitHubpytorchSyntology: not harvested report
CristianoPatricio/zsl-methods mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Contrastive Embedding for Generalized Zero-Shot Learning (arXiv:2103.16173; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
akku1506/Feature-Generating-Networks-for-ZSL mentioned on GitHubtfSyntology: not harvested report
mkara44/f-clswgan_pytorch mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Generalized Zero-Shot LearningZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Zero-Shot Learning SUN Attribute f-CLSWGAN Harmonic mean 39.4 #7 of 9 Archive leaderboard report
Zero-Shot Learning CUB-200-2011 f-CLSWGAN average top-1 classification accuracy 57.3 #12 of 14 Archive leaderboard report
Zero-Shot Learning SUN Attribute f-CLSWGAN average top-1 classification accuracy 60.8 #8 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections