Pith. sign in

REVIEW 2 cited by

Generating images with recurrent adversarial networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1602.05110 v5 pith:UJ5RMUW5 submitted 2016-02-16 cs.LG cs.CV

classification cs.LGcs.CV
keywords adversarialimagesnetworksrecurrentfeaturesimageproposevisual
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality. We show that unrolling this gradient-based optimization yields a recurrent computation that creates images by incrementally adding onto a visual "canvas". We propose a recurrent generative model inspired by this view, and show that it can be trained using adversarial training to generate very good image samples. We also propose a way to quantitatively compare adversarial networks by having the generators and discriminators of these networks compete against each other.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

    cs.CV 2019-09 conditional novelty 5.0 of 10

    A UDA method for semantic segmentation that augments adversarial self-teaching with region growing and class-frequency weighting, with moderate gains over older baselines.

  2. Dueling Deep Q-Learning for Intrusion Detection

    cs.CR 2026-08 reject novelty 4.0 of 10

    A dueling DQN trained as a label-reward classifier on CIC-IDS2018 reports 99.68% average accuracy, but without a held-out test set the accuracy is an in-sample score.

Pith tools