SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.07641 · 2021

Non-deep Networks

arXiv · PDF · Open in the Atlas

Code that ran

12 of 18 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, 1 violated it and 3 have no contract verdict; 7 failures of our instrument; 6 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/2110.07641.json · badge: /api/ran/2110.07641.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
imankgoyal/NonDeepNetworks canonical (classifier label)
classifier basis not recorded on the link
8 ran · 4 no recorded run
hexhowells/Neural-Network-Implementations reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
Pritam-N/ParNet reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
ParNetSmall Ran
ran; our contract draft was wrong, not the code
hexhowells/Neural-Network-Implementations/models/ParNet/parnet.py
code served (permissive licence) · get_code("700f05640a36068a")
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 ParNet. 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,
    "num_classes": 10,
}
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 ParNet — a ParNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ParNet 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
activation_func Ran
ran; our contract draft was wrong, not the code
Pritam-N/ParNet/parnet.py
code served (permissive licence) · get_code("22d0e0cf940313f8")
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 ReLU. 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)

# The function takes a single parameter 'activation' which is a string key
# It uses this key to index into a ModuleDict containing 'relu', 'silu', and 'none'
# We need to provide a valid activation string

ARGS = {
    'activation': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
adapt_input_conv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
imankgoyal/NonDeepNetworks/imagenet/timm/models/helpers.py
code served (permissive licence) · get_code("c58578dcfe39d5e3")
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, shape (2, 3, 4, 4) as a later run recorded it. The image it ran in was 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 math

torch.manual_seed(0)

# Test case 1: in_chans=1, I > 3 (divisible by 3)
in_chans_1 = 1
conv_weight_1 = torch.randn(2, 9, 4, 4)  # O=2, I=9, J=4, K=4

# Test case 2: in_chans=1, I <= 3
in_chans_2 = 1
conv_weight_2 = torch.randn(2, 3, 4, 4)  # O=2, I=3, J=4, K=4

# Test case 3: in_chans=5 (not 1, not 3), I=3
in_chans_3 = 5
conv_weight_3 = torch.randn(2, 3, 4, 4)  # O=2, I=3, J=4, K=4

# Using test case 1
ARGS = {
    "in_chans": 1,
    "conv_weight": torch.randn(2, 9, 4, 4, dtype=torch.float32)
}
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, shape (2, 3, 4, 4) — shape (2, 3, 4, 4) 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: none by the harness; any seed is in the setup block
conv_bn Ran
ran; our contract draft was wrong, not the code
hexhowells/Neural-Network-Implementations/models/ParNet/parnet.py
code served (permissive licence) · get_code("c8af9941c8954a90")
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 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)

ARGS = {
    "in_c": 3,
    "out_c": 16,
    "kernel_size": 3,
    "stride": 1,
    "padding": 1,
    "groups": 1,
}
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 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
conv_sampler Ran
ran; our contract draft was wrong, not the code
Pritam-N/ParNet/parnet.py
code served (permissive licence) · get_code("a2c29db895f66535")
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 partial. 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 functools import partial

torch.manual_seed(0)

ARGS = {
    "kernel_size": 3,
    "stride": 1,
    "groups": 1,
}
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 partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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
downsample_avg Ran
ran; our contract draft was wrong, not the code
imankgoyal/NonDeepNetworks/imagenet/timm/models/resnet.py
code served (permissive licence) · get_code("d0be08be473e0f71")
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)

# Stand-in for AvgPool2dSame if it's not defined
class AvgPool2dSame(nn.Module):
    def __init__(self, kernel_size, stride, ceil_mode=True, count_include_pad=False):
        super().__init__()
        self.kernel_size = kernel_size
        self.stride = stride
        self.ceil_mode = ceil_mode
        self.count_include_pad = count_include_pad
    
    def forward(self, x):
        return nn.functional.avg_pool2d(x, self.kernel_size, self.stride, ceil_mode=self.ceil_mode, count_include_pad=self.count_include_pad)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'kernel_size': 3,
    'stride': 2,
    'dilation': 1,
    'first_dilation': None,
    'norm_layer': nn.BatchNorm2d
}
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
downsample_conv Ran
ran; our contract draft was wrong, not the code
imankgoyal/NonDeepNetworks/imagenet/timm/models/resnet.py
code served (permissive licence) · get_code("eea0376ea397a1c7")
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 ARGS dict with all parameters for downsample_conv
ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 2,
    'dilation': 1,
    'first_dilation': None,
    'norm_layer': nn.BatchNorm2d
}
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
get_padding Ran
ran, honoured the contract we drafted
imankgoyal/NonDeepNetworks/imagenet/timm/models/resnet.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from xslidi/EfficientNets_ddl_apex, is pointer only (licence: NONE) · get_code("9b02c1068795fd5b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from xslidi/EfficientNets_ddl_apex, 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.

is_model Ran
ran, violated the contract we drafted
imankgoyal/NonDeepNetworks/imagenet/timm/models/registry.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("cd2a47ded9dd84cf")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

list_models Ran
ran on a synthesized input
imankgoyal/NonDeepNetworks/imagenet/timm/models/registry.py
code served (permissive licence) · get_code("a7d77cefce03249c")
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 list, ndim 1, 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 re
import fnmatch
from collections import defaultdict

# Set up the global state that list_models depends on
_module_to_models = defaultdict(set)
_model_entrypoints = {}
_model_has_pretrained = set()

# Populate the global state with test data
_module_to_models['resnet'] = {'resnet18', 'resnet34', 'resnet50'}
_module_to_models['efficientnet'] = {'efficientnet_b0', 'efficientnet_b1'}

_model_entrypoints = {
    'resnet18': None,
    'resnet34': None,
    'resnet50': None,
    'efficientnet_b0': None,
    'efficientnet_b1': None,
    'vgg16': None,
    'vgg19': None,
}

_model_has_pretrained = {'resnet18', 'resnet50', 'efficientnet_b0', 'vgg16'}

ARGS = {
    'filter': 'resnet*',
    'module': '',
    'pretrained': False,
    'exclude_filters': '',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
load_state_dict Ran
ran on a synthesized input
imankgoyal/NonDeepNetworks/imagenet/timm/models/helpers.py
code served (permissive licence) · get_code("bc3a13e8155e8140")
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 OrderedDict. 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 os
import tempfile
from collections import OrderedDict

torch.manual_seed(0)

# Create a temporary checkpoint file with a valid state dict
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, "checkpoint.pt")

# Create a sample state dict
state_dict = OrderedDict([
    ("layer1.weight", torch.randn(4, 3)),
    ("layer1.bias", torch.randn(4)),
    ("module.layer2.weight", torch.randn(5, 4)),
])

# Create checkpoint dict with both regular and EMA state dicts
checkpoint = {
    "state_dict": state_dict,
    "state_dict_ema": OrderedDict([
        ("layer1.weight", torch.randn(4, 3)),
        ("layer1.bias", torch.randn(4)),
        ("layer2.weight", torch.randn(5, 4)),
    ]),
    "epoch": 10,
}

# Save checkpoint
torch.save(checkpoint, checkpoint_path)

ARGS = {
    "checkpoint_path": checkpoint_path,
    "use_ema": False,
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
register_model Ran
ran on a synthesized input
imankgoyal/NonDeepNetworks/imagenet/timm/models/registry.py
code served (permissive licence) · get_code("99e9e0964c9cad5a")
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 function. 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 sys
from types import ModuleType

# Create a mock module with necessary attributes
mock_module = ModuleType('test_module')
mock_module.__name__ = 'test_module'
mock_module.__all__ = []

# Create a mock function to be registered
def mock_model_fn():
    pass

mock_model_fn.__module__ = 'test_module'
mock_model_fn.__name__ = 'test_model'

# Register the mock module in sys.modules so the function can find it
sys.modules['test_module'] = mock_module

# Add default_cfgs to the module (with a model that has pretrained weights)
mock_module.default_cfgs = {
    'test_model': {
        'url': 'https://example.com/weights.pth',
        'num_classes': 1000
    }
}

ARGS = {
    'fn': mock_model_fn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
broadcast_receive Not yet run
unverified (harvested, no recorded run)
imankgoyal/NonDeepNetworks/imagenet/timm/models/simplenet.py
code served (permissive licence) · get_code("c2dbae15a7438840")
How it ran

no invocation recorded.

conv_bn Not yet run
unverified (harvested, no recorded run)
Pritam-N/ParNet/parnet.py
code served (permissive licence) · get_code("ce72bd6274c553ef")
How it ran

no invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
imankgoyal/NonDeepNetworks/imagenet/timm/models/factory.py
code served (permissive licence) · get_code("8819f9c15124c943")
How it ran

no invocation recorded.

receive Not yet run
unverified (harvested, no recorded run)
imankgoyal/NonDeepNetworks/imagenet/timm/models/simplenet.py
code served (permissive licence) · get_code("b6b952edfef8899a")
How it ran

no invocation recorded.

resume_checkpoint Not yet run
unverified (harvested, no recorded run)
imankgoyal/NonDeepNetworks/imagenet/timm/models/helpers.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("102b75f3481035d1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from Wenhao-Chi/UNIEGO, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

scale_dim Not yet run
unverified (harvested, no recorded run)
hexhowells/Neural-Network-Implementations/models/ParNet/parnet.py
code served (permissive licence) · get_code("b39c1c629a22b4fe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 7 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 7 later) and 11 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
is_model 22 other papers
6 dated earlier, 16 later
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 19 more not named here
get_padding 10 other papers
1 dated earlier, 9 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
2205.13490 (2022-05)
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
and 7 more not named here
downsample_conv 7 other papers
7 later
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
2205.13490 (2022-05)
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
2208.10169 (2022-08)
Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation
and 4 more not named here
adapt_input_conv 6 other papers
1 the same month, 5 later
2110.05069 (2021-10)
Efficient Training of Audio Transformers with Patchout
2204.07683 (2022-04)
Safe Self-Refinement for Transformer-based Domain Adaptation
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 3 more not named here
downsample_avg 6 other papers
6 later
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
2205.13490 (2022-05)
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
2208.10169 (2022-08)
Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation
and 3 more not named here
resume_checkpoint 6 other papers
6 later
2203.10233 (2022-03)
DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
2210.04135 (2022-10)
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
and 3 more not named here
load_state_dict 1 other paper
1 later
2210.04135 (2022-10)
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment

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

Depth is the hallmark of deep neural networks. But more depth means more sequential computation and higher latency. This begs the question -- is it possible to build high-performing "non-deep" neural networks? We show that it is. To do so, we use parallel subnetworks instead of stacking one layer after another. This helps effectively reduce depth while maintaining high performance. By utilizing parallel substructures, we show, for the first time, that a network with a depth of just 12 can achieve top-1 accuracy over 80% on ImageNet, 96% on CIFAR10, and 81% on CIFAR100. We also show that a network with a low-depth (12) backbone can achieve an AP of 48% on MS-COCO. We analyze the scaling rules for our design and show how to increase performance without changing the network's depth. Finally, we provide a proof of concept for how non-deep networks could be used to build low-latency recognition systems. Code is available at https://github.com/imankgoyal/NonDeepNetworks.

For agents

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

get_harvested_code_for_paper("2110.07641")
get_code_for_paper("2110.07641")
have("2110.07641")

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

curl https://syntology.ai/api/ran/2110.07641.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.07641.svg)](https://syntology.ai/paper/2110.07641)

Connect an agent — have() is free.