SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.01002 · ICML · 2024

Spider : A Unified Framework for Context-dependent Concept Segmentation

Wei Ji, Xiaoqi Zhao, Youwei Pang, Baicheng Sheng, Jiaming Zuo, Lihe Zhang, Huchuan Lu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 2 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/2405.01002.json · badge: /api/ran/2405.01002.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
xiaoqi-zhao-dlut/spider-unicdseg canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
ASPP Ran
ran on a synthesized input · constructed an object; no result was computed
xiaoqi-zhao-dlut/spider-unicdseg/model/DBS_group_prompt.py
pointer only (licence: NONE) · get_code("134d2a21569d49b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqi-zhao-dlut/spider-unicdseg 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.

Attention Ran
ran on a synthesized input · constructed an object; no result was computed
xiaoqi-zhao-dlut/spider-unicdseg/model/DBS_group_prompt.py
pointer only (licence: NONE) · get_code("68ed7eb275807bb1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqi-zhao-dlut/spider-unicdseg 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.

CrossTransformer Ran
ran on a synthesized input · constructed an object; no result was computed
xiaoqi-zhao-dlut/spider-unicdseg/model/DBS_group_prompt.py
pointer only (licence: NONE) · get_code("b93a2ef28ce380ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqi-zhao-dlut/spider-unicdseg 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.

FoldConv_aspp Ran
ran on a synthesized input · constructed an object; no result was computed
Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency/model/GateNetv2_rgb_d_res50.py
code served (permissive licence) · get_code("09772467ed6b580c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, FoldConv_aspp: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define ARGS dict with all parameters for FoldConv_aspp.__init__
ARGS = {
    'in_channel': 3,
    'out_channel': 4,
    'out_size': 32,
    'kernel_size': 3,
    'stride': 1,
    'padding': 0,
    'dilation': 1,
    'groups': 1,
    'win_size': 2,
    'win_dilation': 1,
    'win_padding': 0,
}

# Create instance to verify it works
model = nn.Module.__new__(type('FoldConv_aspp', (nn.Module,), {}))
# Verify ARGS has all required parameters
required_params = {
    'in_channel', 'out_channel', 'out_size', 'kernel_size', 
    'stride', 'padding', 'dilation', 'groups', 'win_size', 
    'win_dilation', 'win_padding'
}
assert set(ARGS.keys()) == required_params, f"Missing parameters: {required_params - set(ARGS.keys())}"
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FoldConv_aspp — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FoldConv_aspp output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
GateNetv2_two_stream Not yet run
unverified (harvested, no recorded run)
Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency/model/GateNetv2_rgb_d_res50.py
code served (permissive licence) · get_code("967a49745a26f863")
How it ran

no invocation recorded.

Spider_ConvNeXt Not yet run
unverified (harvested, no recorded run)
xiaoqi-zhao-dlut/spider-unicdseg/model/DBS_group_prompt.py
pointer only (licence: NONE) · get_code("181f5b1b2e2a53ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqi-zhao-dlut/spider-unicdseg 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Different from the context-independent (CI) concepts such as human, car, and airplane, contextdependent (CD) concepts require higher visual understanding ability, such as camouflaged object and medical lesion. Despite the rapid advance of many CD understanding tasks in respective branches, the isolated evolution leads to their limited cross-domain generalisation and repetitive technique innovation. Since there is a strong coupling relationship between foreground and background context in CD tasks, existing methods require to train separate models in their focused domains. This restricts their real-world CD concept understanding towards artificial general intelligence (AGI). We propose a unified model with a single set of parameters, Spider, which only needs to be trained once. With the help of the proposed concept filter driven by the image-mask group prompt, Spider is able to understand and distinguish diverse strong context-dependent concepts to accurately capture the Prompter's intention. Without bells and whistles, Spider significantly outperforms the state-of-the-art specialized models in 8 different context-dependent segmentation tasks, including 4 natural scenes (salient, camouflaged, and transparent objects and shadow) and 4 medical lesions (COVID-19, polyp, breast, and skin lesion with color colonoscopy, CT, ultrasound, and dermoscopy modalities). Besides, Spider shows obvious advantages in continuous learning. It can easily complete the training of new tasks by fine-tuning parameters less than 1% and bring a tolerable performance degradation of less than 5% for all old tasks. The source code will be publicly available at Spider-UniCDSeg.

For agents

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

get_harvested_code_for_paper("2405.01002")
get_code_for_paper("2405.01002")
have("2405.01002")

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

curl https://syntology.ai/api/ran/2405.01002.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.01002.svg)](https://syntology.ai/paper/2405.01002)

Connect an agent — have() is free.