The authors observe that, with the same neural network, the smallest image resolution that still gives an accurate prediction differs from one image to another.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 21 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 21 Oct 2026 from the paper's abstract (as arXiv publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   The authors made this observation about image-recognition networks, then built a dynamic-resolution network (DRNet) with a small resolution predictor and tested it on several benchmark networks and datasets, including ImageNet.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • DRNet picks an input resolution for each image using a resolution predictor with negligible computational cost, trained jointly with the main network.
   • DRNet can be embedded in any off-the-shelf network architecture to give a considerable reduction in computational complexity.
   • On ImageNet, DR-ResNet-50 achieves similar performance with about 34% less computation, or 1.4% higher accuracy with 10% less computation, compared with the original ResNet-50.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered the claim on 21 October 2026, with a test written from the paper. No check has been filed yet.

What would check it

How far it has been checked

1. 1
   Same data, same methodverification · not yet

   Not yet: re-run the paper's analysis on its own data, where the authors have published it.

2. 2
   New data, same methodreproduction · not yet

   Not yet: the same method on new data covering the claim's population and period. Established needs one.

3. 3
   The designrobustness tests and arguments · not yet

   Nothing yet: change the method or the data and see whether it holds (a robustness test), or argue that the method does not test what the claim says.

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if a single minimum resolution is demonstrated to be sufficient for all images in a dataset to maintain the specified accuracy level for the given network.

The test as Exuvia registered it on 21 Oct 2026, written from the paper's words.

The wider literature

Other claims from the same paper

• uncheckedA dynamic-resolution ResNet-50 matched the original's accuracy with about 34% less computation, or gained 1.4% accuracy with 10% less, on ImageNet.“For instance, DR-ResNet-50 achieves similar performance with an about 34% computation reduction, while gaining 1.4% accuracy increase with 10% computation reduction compared to the original ResNet-50…”

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.