SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.06697 · ECCV · 2022

Efficient Long-Range Attention Network for Image Super-resolution

Lei Zhang, Hui Zeng, Shi Guo, Xindong Zhang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 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/2203.06697.json · badge: /api/ran/2203.06697.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
xindongzhang/ELAN community
Papers with Code archive
6 ran · 2 no recorded run
FunctionStatusWhere it lives
GMSA Ran
ran on a synthesized input · constructed an object; no result was computed
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("dfe23f9c73fba360")
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, GMSA: 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
from einops import rearrange

torch.manual_seed(0)

# Create a minimal valid input tensor
# Shape: (batch=2, channels=12, height=16, width=16)
# height and width must be divisible by all window_sizes [4, 8, 12]
x = torch.randn(2, 12, 16, 16)

# Test that the module can be instantiated and run
ARGS = {
    "channels": 12,
    "shifts": 4,
    "window_sizes": [4, 8, 12],
    "calc_attn": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GMSA — 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 GMSA 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
LFE Ran
ran on a synthesized input · constructed an object; no result was computed
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("e2f3cf4b805acd22")
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, LFE: 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)

# Minimal setup for LFE
ARGS = {
    'inp_channels': 10,
    'out_channels': 5,
    'exp_ratio': 4,
    'act_type': 'relu'
}
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 LFE — 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 LFE 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
MeanShift Ran
ran on a synthesized input · constructed an object; no result was computed
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("d490b61d417da427")
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, MeanShift: 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)

ARGS = {
    'rgb_range': 255,
    'rgb_mean': (0.4488, 0.4371, 0.404),
    'rgb_std': (1.0, 1.0, 1.0),
    'sign': -1
}
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 MeanShift — 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 MeanShift 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
ShiftConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("e096da98ed9b4c9b")
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, ShiftConv2d: 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)

# Create a small input tensor for testing
# Shape: (batch=2, channels=10, height=4, width=3)
x = torch.randn(2, 10, 4, 3)

ARGS = {
    'inp_channels': 10,
    'out_channels': 5,
    'conv_type': 'fast-training-speed'
}
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 ShiftConv2d — 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 ShiftConv2d 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
ShiftConv2d0 Ran
ran on a synthesized input · constructed an object; no result was computed
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("66d05bc6340179bf")
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, ShiftConv2d0: 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)

# Create a small input tensor for testing
# Shape: (batch=2, channels=20, height=4, width=4)
x = torch.randn(2, 20, 4, 4)

# ShiftConv2d0 takes inp_channels and out_channels as arguments
inp_channels = 20
out_channels = 16

ARGS = {
    'inp_channels': inp_channels,
    'out_channels': out_channels
}
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 ShiftConv2d0 — 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 ShiftConv2d0 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
ShiftConv2d1 Ran
ran on a synthesized input · constructed an object; no result was computed
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("41750d8ae4ed5bb6")
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, ShiftConv2d1: 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)

# Create a simple input tensor: batch_size=2, channels=20, height=4, width=4
x = torch.randn(2, 20, 4, 4)

# Define the arguments for ShiftConv2d1.__init__
# inp_channels must be divisible by n_div (5), so use 20
# out_channels can be any value, use 16 for distinctness
inp_channels = 20
out_channels = 16

ARGS = {
    'inp_channels': inp_channels,
    'out_channels': out_channels,
}
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 ShiftConv2d1 — 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 ShiftConv2d1 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
ELAB Not yet run
unverified (harvested, no recorded run)
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("0d8891855a2a0b6b")
How it ran

no invocation recorded.

ELAN Not yet run
unverified (harvested, no recorded run)
xindongzhang/ELAN/models/elan_network.py
code served (permissive licence) · get_code("50a985088fff2f68")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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, 1 later) and 7 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
MeanShift
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 1 the same month, 1 later
1807.02758 (2018-07)
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
2203.04963 (2022-03)
Neural Data-Dependent Transform for Learned Image Compression
2303.16890 (2023-03)
DPF: Learning Dense Prediction Fields with Weak Supervision

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

Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for feature extraction. However, the computation of SA in most existing transformer based models is very expensive, while some employed operations may be redundant for the SR task. This limits the range of SA computation and consequently limits the SR performance. In this work, we propose an efficient long-range attention network (ELAN) for image SR. Specifically, we first employ shift convolution (shift-conv) to effectively extract the image local structural information while maintaining the same level of complexity as 1x1 convolution, then propose a group-wise multi-scale self-attention (GMSA) module, which calculates SA on non-overlapped groups of features using different window sizes to exploit the long-range image dependency. A highly efficient long-range attention block (ELAB) is then built by simply cascading two shift-conv with a GMSA module, which is further accelerated by using a shared attention mechanism. Without bells and whistles, our ELAN follows a fairly simple design by sequentially cascading the ELABs. Extensive experiments demonstrate that ELAN obtains even better results against the transformer-based SR models but with significantly less complexity. The source codes of ELAN can be found at https://github.com/xindongzhang/ELAN.

For agents

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

get_harvested_code_for_paper("2203.06697")
get_code_for_paper("2203.06697")
have("2203.06697")

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

curl https://syntology.ai/api/ran/2203.06697.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.06697.svg)](https://syntology.ai/paper/2203.06697)

Connect an agent — have() is free.