SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03619 · 2022

Adaptive Cross-Layer Attention for Image Restoration

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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 2 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/2203.03619.json · badge: /api/ran/2203.03619.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
sdl-asu/acla canonical (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
default_conv Ran
ran; our contract draft was wrong, not the code
sdl-asu/acla/SR/model/common.py
code served (permissive licence) · get_code("8b0e794d4d8f9b13")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Conv2d. 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)

ARGS = {
    'in_channels': 3,
    'out_channels': 5,
    'kernel_size': 3,
    'bias': True
}
Setup block drafted by
a language model, Claude Sonnet 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
deform_conv2d Ran
ran on a synthesized input
sdl-asu/acla/SR/model/ACL_Attention.py
code served (permissive licence) · get_code("74343d6a0353947e")
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 Tensor, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from typing import Optional, Tuple

torch.manual_seed(0)

# Build tiny tensors for deform_conv2d
batch_size = 2
in_channels = 3
out_channels = 4
height = 5
width = 5
kernel_h = 3
kernel_w = 3

# Input tensor: (batch, in_channels, height, width)
input_tensor = torch.randn(batch_size, in_channels, height, width)

# Weight tensor: (out_channels, in_channels, kernel_h, kernel_w)
weight_tensor = torch.randn(out_channels, in_channels, kernel_h, kernel_w)

# Offset tensor: (batch, 2 * kernel_h * kernel_w, out_height, out_width)
# With stride=1, padding=0, dilation=1: out_height = height - kernel_h + 1 = 3
out_height = height - kernel_h + 1
out_width = width - kernel_w + 1
offset_tensor = torch.randn(batch_size, 2 * kernel_h * kernel_w, out_height, out_width)

# Bias tensor: (out_channels,)
bias_tensor = torch.randn(out_channels)

# Mask tensor: (batch, kernel_h * kernel_w, out_height, out_width)
mask_tensor = torch.ones(batch_size, kernel_h * kernel_w, out_height, out_width)

# Stride, padding, dilation as tuples
stride = (1, 1)
padding = (0, 0)
dilation = (1, 1)

ARGS = {
    "input": input_tensor,
    "offset": offset_tensor,
    "weight": weight_tensor,
    "bias": bias_tensor,
    "stride": stride,
    "padding": padding,
    "dilation": dilation,
    "mask": mask_tensor,
}
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 Tensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AttributeError)
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: none by the harness; any seed is in the setup block
get_parameter_number Ran
ran; our contract draft was wrong, not the code
sdl-asu/acla/SR/model/common.py
pointer only (licence: MIT); the stored copy get_code serves, from zzzx1224/ebtsa-iclr2023, is pointer only (licence: NONE) · get_code("b2fb8159f199e5b8")
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 zzzx1224/ebtsa-iclr2023, 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.

make_same_layer_superimposed Ran
ran on a synthesized input
sdl-asu/acla/SR/model/common.py
code served (permissive licence) · get_code("415fea29e966e23f")
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 Sequential. 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 a simple block class that can be instantiated multiple times
class SimpleBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# The function uses:
# - block: a callable that returns an nn.Module (called n_layers times)
# - n_layers: an integer specifying how many times to stack the block

ARGS = {
    "block": SimpleBlock,
    "n_layers": 3
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make_model Not yet run
unverified (harvested, no recorded run)
sdl-asu/acla/SR/model/carn.py
code served (permissive licence) · get_code("5ecf1cc45bcc3af5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 3 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
default_conv 57 other papers
15 dated earlier, 3 the same month, 38 later, 1 same year, order not determinable · 2 only as an assembly brick
1707.02921 (2017-07)
Enhanced Deep Residual Networks for Single Image Super-Resolution
1803.02735 (2018-03)
Deep Back-Projection Networks For Super-Resolution
1803.04626 (2018-03)
Maintaining Natural Image Statistics with the Contextual Loss
and 54 more not named here
get_parameter_number 3 other papers
3 later
2302.11215 (2023-02)
Energy-Based Test Sample Adaptation for Domain Generalization
2308.13894 (2023-08)
FwdLLM: Efficient FedLLM using Forward Gradient
2404.03637 (2024-04)
Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention

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

Non-local attention module has been proven to be crucial for image restoration. Conventional non-local attention processes features of each layer separately, so it risks missing correlation between features among different layers. To address this problem, we aim to design attention modules that aggregate information from different layers. Instead of finding correlated key pixels within the same layer, each query pixel is encouraged to attend to key pixels at multiple previous layers of the network. In order to efficiently embed such attention design into neural network backbones, we propose a novel Adaptive Cross-Layer Attention (ACLA) module. Two adaptive designs are proposed for ACLA: (1) adaptively selecting the keys for non-local attention at each layer; (2) automatically searching for the insertion locations for ACLA modules. By these two adaptive designs, ACLA dynamically selects a flexible number of keys to be aggregated for non-local attention at previous layer while maintaining a compact neural network with compelling performance. Extensive experiments on image restoration tasks, including single image super-resolution, image denoising, image demosaicing, and image compression artifacts reduction, validate the effectiveness and efficiency of ACLA. The code of ACLA is available at \url{https://github.com/SDL-ASU/ACLA}.

For agents

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

get_harvested_code_for_paper("2203.03619")
get_code_for_paper("2203.03619")
have("2203.03619")

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

curl https://syntology.ai/api/ran/2203.03619.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03619.svg)](https://syntology.ai/paper/2203.03619)

Connect an agent — have() is free.