SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.04009 · NeurIPS · 2024

Structured Click Control in Transformer-based Interactive Segmentation

Rui Huang, Feng Wu, Long Xu, Yongquan Chen, Shiwu Lai

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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; 1 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 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/2405.04009.json · badge: /api/ran/2405.04009.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
hahamyt/scc canonical (classifier label)
classifier basis: classifier_2025
8 ran · 1 no recorded run
FunctionStatusWhere it lives
AdjBlock Ran
ran on a synthesized input
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("e3da1afeb3144e27")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

CrossAttention Ran
ran on a synthesized input
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("df5cfe9ca081ba57")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

GAT Ran
ran on a synthesized input
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("1d174c7f1898b9b2")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

GraphAttentionLayer Ran
ran on a synthesized input
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("6e2dfb3168df266d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

SimBlock Ran
ran on a synthesized input
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("da0250470ea50ce7")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

calculate_binary_cigr Ran
ran, honoured the contract we drafted
hahamyt/scc/scripts/evaluate_model.py
pointer only (licence: GPL-3.0) · get_code("fe573f7a27b979af")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

get_predictor_and_zoomin_params Ran
ran; our contract draft was wrong, not the code
hahamyt/scc/scripts/evaluate_model.py
pointer only (licence: GPL-3.0) · get_code("fca7b0a20cde7062")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

mean_query Ran
ran; our contract draft was wrong, not the code
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("797caf177e62b27e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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.

GATFusionBlock Not yet run
unverified (harvested, no recorded run)
hahamyt/scc/isegm/model/modeling/gatlayers.py
pointer only (licence: GPL-3.0) · get_code("7af6422c5e3a96fe")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, hahamyt/scc, is not in the permissive set Syntology serves inline. 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 0 later) and 8 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
get_predictor_and_zoomin_params 2 other papers
1 dated earlier, 1 the same month
2210.11006 (2022-10)
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers
2405.00587 (2024-05)
GraCo: Granularity-Controllable Interactive Segmentation

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

Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation results tend to have little change or are even worse than before. To improve the robustness of the response, we propose a structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens. Then the graph nodes will be aggregated to obtain structured interaction features. Finally, the dual cross-attention will be used to inject structured interaction features into vision Transformer features, thereby enhancing the control of clicks over segmentation results. Extensive experiments demonstrated the proposed algorithm can serve as a general structure in improving Transformer-based interactive segmentation performance. The code and data will be released at SCC.

For agents

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

get_harvested_code_for_paper("2405.04009")
get_code_for_paper("2405.04009")
have("2405.04009")

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

curl https://syntology.ai/api/ran/2405.04009.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.04009.svg)](https://syntology.ai/paper/2405.04009)

Connect an agent — have() is free.