SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.00314 · ICLR · 2024

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Sangwoo Mo, Stella Yu, Tsung-Wei Ke

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2210.00314.json · badge: /api/ran/2210.00314.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
twke18/CAST canonical (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_principal_components Ran
ran; our contract draft was wrong, not the code
twke18/CAST/cast_models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from pseulki/hcast, is pointer only (licence: NONE) · get_code("752d44ef2ecdfbec")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pseulki/hcast, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resize_labels Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
twke18/CAST/cast_models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from pseulki/hcast, is pointer only (licence: NONE) · get_code("0e0244ff28c52bfc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pseulki/hcast, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

valid_mean Ran
ran; our contract draft was wrong, not the code
twke18/CAST/cast_models/graph_pool.py
pointer only (licence: MIT); the stored copy get_code serves, from pseulki/hcast, is pointer only (licence: NONE) · get_code("fdb43f0017ed684b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pseulki/hcast, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pca Not yet run
unverified (harvested, no recorded run)
twke18/CAST/cast_models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from pseulki/hcast, is pointer only (licence: NONE) · get_code("1bff6d0d888ca2c3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pseulki/hcast, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
calculate_principal_components 1 other paper
1 later
2406.11608 (2024-06)
Visually Consistent Hierarchical Image Classification
pca 1 other paper
1 later
2406.11608 (2024-06)
Visually Consistent Hierarchical Image Classification
resize_labels 1 other paper
1 later
2406.11608 (2024-06)
Visually Consistent Hierarchical Image Classification
valid_mean 1 other paper
1 later
2406.11608 (2024-06)
Visually Consistent Hierarchical Image Classification

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large vision and language models learned directly through image-text associations often lack detailed visual substantiation, whereas image segmentation tasks are treated separately from recognition, supervisedly learned without interconnections. Our key observation is that, while an image can be recognized in multiple ways, each has a consistent part-and-whole visual organization. Segmentation thus should be treated not as an end task to be mastered through supervised learning, but as an internal process that evolves with and supports the ultimate goal of recognition. We propose to integrate a hierarchical segmenter into the recognition process, train and adapt the entire model solely on image-level recognition objectives. We learn hierarchical segmentation for free alongside recognition, automatically uncovering part-to-whole relationships that not only underpin but also enhance recognition. Enhancing the Vision Transformer (ViT) with adaptive segment tokens and graph pooling, our model surpasses ViT in unsupervised part-whole discovery, semantic segmentation, image classification, and efficiency. Notably, our model (trained on unlabeled 1M ImageNet images) outperforms SAM (trained on 11M images and 1 billion masks) by absolute 8% in mIoU on PartImageNet object segmentation. * Equal contribution. Code available at https://github.com/twke18/CAST.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.00314")
get_code_for_paper("2210.00314")
have("2210.00314")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.00314.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.00314.svg)](https://syntology.ai/paper/2210.00314)

Connect an agent — have() is free.