SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.18888 · 2026

Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis

Lu Liu, Gaojie Jin, Di Wang, Lu Yin, Xiang Li, Tianjin Huang, Lijie Hu, Yanda Meng, Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; 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/2602.18888.json · badge: /api/ran/2602.18888.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
misswayguy/DKA community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
DW5_51 Ran
ran on a synthesized input
misswayguy/DKA/experiments/cnn/profile_dka_kernels.py
code served (permissive licence) · get_code("6c0d49bb46e5aeb8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 192, 4, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape 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

C = 192

device = 'cpu'

def make_dw_conv(C, k):
    padding = k // 2
    conv = nn.Conv2d(in_channels=C, out_channels=C, kernel_size=k, padding=padding, groups=C, bias=False)
    return conv.to(device).eval()

class DW5_51(nn.Module):

    def __init__(self, C):
        super().__init__()
        self.dw5 = make_dw_conv(C, 5)
        self.dw51 = make_dw_conv(C, 51)

    def forward(self, x):
        return self.dw5(x) + self.dw51(x)


INIT_ARGS = {
    'C': 192
}

ARGS = {
    'x': torch.randn(2, 192, 4, 3)
}

if __name__ == '__main__':
    model = DW5_51(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output dtype: {output.dtype}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 192, 4, 3) — shape (2, 192, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
make_dw_conv Ran
ran; our contract draft was wrong, not the code
misswayguy/DKA/experiments/cnn/profile_dka_kernels.py
code served (permissive licence) · get_code("7631b6cc36d2deee")
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) and returned Conv2d. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# The function make_dw_conv takes two parameters:
# - C: an integer representing the number of channels
# - k: an integer representing the kernel size

ARGS = {
    'C': 192,
    'k': 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Adapters have become a widely adopted strategy for efficient fine-tuning of large pretrained models, particularly in resource-constrained settings. However, their performance under extreme data scarcity-common in medical imaging due to high annotation costs, privacy regulations, and fragmented datasets-remains underexplored. In this work, we present the first comprehensive study of adapter-based fine-tuning for large pretrained models in low-data medical imaging scenarios. We find that, contrary to their promise, conventional Adapters can degrade performance under severe data constraints, performing even worse than simple linear probing when trained on less than 1% of the corresponding training data. Through systematic analysis, we identify a sharp reduction in Effective Receptive Field (ERF) as a key factor behind this degradation. Motivated by these findings, we propose the Dual-Kernel Adapter (DKA), a lightweight module that expands spatial context via large-kernel convolutions while preserving local detail with small-kernel counterparts. Extensive experiments across diverse classification and segmentation benchmarks show that DKA significantly outperforms existing Adapter methods, establishing new leading results in both data-constrained and data-rich regimes. Code is available at https://github.com/misswayguy/DKA.

For agents

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

get_harvested_code_for_paper("2602.18888")
get_code_for_paper("2602.18888")
have("2602.18888")

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

curl https://syntology.ai/api/ran/2602.18888.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.18888.svg)](https://syntology.ai/paper/2602.18888)

Connect an agent — have() is free.