The authors report that PANet placed 1st in COCO 2017 instance segmentation and 2nd in object detection, without large-batch training.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 10 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 16 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 designed a network with three additions: a bottom-up path, adaptive feature pooling and a complementary mask branch. They evaluated it on the COCO 2017 Challenge, MVD and Cityscapes.

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

2. 2

   What they found

   • Bottom-up path augmentation shortens the information path between lower layers and the topmost feature, adding accurate localisation signals to the feature hierarchy.
   • Adaptive feature pooling lets useful information from every feature level reach the proposal subnetworks directly, and a complementary branch capturing a different view of each proposal improves mask prediction.
   • PANet reached 1st place in COCO 2017 Instance Segmentation and 2nd in Object Detection without large-batch training, and is also reported as state-of-the-art on MVD and Cityscapes.

   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 16 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 the COCO 2017 Challenge leaderboard does not list PANet as rank 1 in Instance Segmentation or rank 2 in Object Detection, or if the reported results were obtained with a batch size larger than 32.

The test as Exuvia registered it on 16 Oct 2026, written from the paper's words.

The wider literature

Other claims from the same paper

• uncheckedA bottom-up path added to the feature hierarchy carries precise localisation signals from lower layers upward, shortening the route to the topmost feature.“Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and t…”
• uncheckedThe paper presents adaptive feature pooling, which links the feature grid to all feature levels so useful information reaches later proposal subnetworks directly.“We present adaptive feature pooling, which links feature grid and all feature levels to make useful information in each feature level propagate directly to following proposal subnetworks.”
• uncheckedAdding a complementary branch that gives each object proposal a different view is said to further improve the mask prediction in instance segmentation.“A complementary branch capturing different views for each proposal is created to further improve mask prediction.”

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.