HackerPapers

arXiv:2204.13807cs.CV

A very preliminary analysis of DALL-E 2

Gary Marcus, Ernest Davis, Scott Aaronson

Abstract

The DALL-E 2 system generates original synthetic images corresponding to an input text as caption. We report here on the outcome of fourteen tests of this system designed to assess its common sense, reasoning and ability to understand complex texts. All of our prompts were intentionally much more challenging than the typical ones that have been showcased in recent weeks. Nevertheless, for 5 out of the 14 prompts, at least one of the ten images fully satisfied our requests. On the other hand, on no prompt did all of the ten images satisfy our requests.

arXiv comments
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.AIArtificial Intelligence

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from May 2022 to Oct 2022. Found in 1 HN submission from May 2022 to May 2022. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. Imagen Video: high definition video generation with diffusion models 1 comment

    • Relationships between objects has been a problem with computer vision for a long time. 10 years ago: https://karpathy.github.io/2012/10/22/state-of-computer-visi... Now: https://arxiv.org/pdf/2204.13807 Given that this is what makes photos and videos interesting I think it's…

      rcptView on HNParent context

  2. Is DALL-E 2 ‘gluing things together’ without understanding their relationships? 1 comment

    • > Are you sure? Considering Dall-e has problems painting "a red cube on top of a blue cube" [1] and all kind of simple spatial relations, I'd say it's a fair shot. [1] As reported by OpenAI, but there are also some prompts by Gary Marcus et al. (https://arxiv.org/abs/2204.13807)…

      gattilorenzView on HNParent context

  3. A preliminary analysis of DALL-E 2 (Marcus, Davis, Aaronson) 1 comment

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.