SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.01801 · ICCV · 2021

Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation

Lin Wang, Kuk-Jin Yoon, Yujeong Chae

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 failures of our instrument; 3 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/2109.01801.json · badge: /api/ran/2109.01801.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
addisonwang2013/dtl canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
addisonwang2013/DTL community
Papers with Code archive
2 ran · 3 no recorded run
FunctionStatusWhere it lives
EITConv Ran
ran on a synthesized input · constructed an object; no result was computed
addisonwang2013/DTL/modeling/deeplab_dtl.py
code served (permissive licence) · get_code("9660609a6d6cbf98")
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, EITConv: 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

torch.manual_seed(0)

class EITConv(torch.nn.Module):

    def __init__(self, in_ch, out_ch):
        super(EITConv, self).__init__()
        self.conv = torch.nn.Sequential(torch.nn.Conv2d(in_ch, out_ch, 3, padding=1), torch.nn.ReLU(inplace=True), torch.nn.Conv2d(out_ch, out_ch, 3, padding=1))
        self.residual_upsampler = torch.nn.Sequential(torch.nn.Conv2d(in_ch, out_ch, kernel_size=1, bias=False))

    def forward(self, input):
        return self.conv(input) + self.residual_upsampler(input)

ARGS = {
    'in_ch': 3,
    'out_ch': 4
}
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 EITConv — 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 EITConv 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
build_aspp Ran
ran; our contract draft was wrong, not the code
addisonwang2013/DTL/modeling/deeplab_dtl.py
code served (permissive licence) · get_code("39265c6363db075a")
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 ASPP_EIT. 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)

class _ASPPModule(nn.Module):
    def __init__(self, inplanes, outplanes, kernel_size, padding, dilation, BatchNorm):
        super(_ASPPModule, self).__init__()
        self.atrous_conv = nn.Conv2d(inplanes, outplanes, kernel_size=kernel_size,
                                     stride=1, padding=padding, dilation=dilation, bias=False)
        self.bn = BatchNorm(outplanes)
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.atrous_conv(x)
        x = self.bn(x)
        x = self.relu(x)
        return x

class SynchronizedBatchNorm2d(nn.Module):
    def __init__(self, num_features):
        super(SynchronizedBatchNorm2d, self).__init__()
        self.bn = nn.BatchNorm2d(num_features)
        self.weight = self.bn.weight
        self.bias = self.bn.bias

    def forward(self, x):
        return self.bn(x)

# Test for ASPP
x_aspp = torch.randn(2, 2048, 4, 4)

ARGS = {
    'backbone': 'resnet',
    'output_stride': 16,
    'BatchNorm': 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 ASPP_EIT — a ASPP_EIT output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ASPP_EIT 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
addisonwang2013/dtl/backbone/drn.py
code served (permissive licence) · get_code("0e722c9ff0920473")
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 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_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "padding": 1,
    "dilation": 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 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
conv_bn Ran
ran on a synthesized input
addisonwang2013/dtl/backbone/mobilenet.py
code served (permissive licence) · get_code("8cf426bba4e98da5")
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)

ARGS = {
    'inp': 3,
    'oup': 16,
    'stride': 1,
    'BatchNorm': 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
decode_segmap Ran
ran on a synthesized input
addisonwang2013/dtl/visualize.py
code served (permissive licence) · get_code("d50d152c6a2002ce")
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 ndarray, ndim 3, dtype family float, shape (3, 4, 3) 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 numpy as np

# Create a small segmentation map with values 0-5 (class labels)
# The function expects a 2D array where each element is a class label (0-5)
temp = np.array([
    [0, 1, 2, 3],
    [4, 5, 0, 1],
    [2, 3, 4, 5]
], dtype=np.int32)

ARGS = {
    "temp": temp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 4, 3) — shape (3, 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: none by the harness; any seed is in the setup block
fixed_padding Ran
ran on a synthesized input
addisonwang2013/dtl/backbone/mobilenet.py
code served (permissive licence) · get_code("b34c12741c44b60c")
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, 4, 7, 9) 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 torch.nn.functional as F

torch.manual_seed(0)

# Construct a small 4D tensor (batch, channels, height, width)
inputs = torch.randn(2, 4, 3, 5)

# Construct scalar parameters
kernel_size = 3
dilation = 2

ARGS = {
    "inputs": inputs,
    "kernel_size": kernel_size,
    "dilation": dilation,
}
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, 4, 7, 9) — shape (2, 4, 7, 9) 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
xception Ran
ran on a synthesized input
addisonwang2013/dtl/backbone/xception_new.py
code served (permissive licence) · get_code("fd487be36b369be6")
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 Xception. 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 = {
    'BatchNorm': nn.BatchNorm2d,
    'pretrained': 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 Xception — a Xception output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Xception 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
ASPP_EIT Not yet run
unverified (harvested, no recorded run)
addisonwang2013/DTL/modeling/deeplab_dtl.py
code served (permissive licence) · get_code("40529a28fb8f1e37")
How it ran

no invocation recorded.

ASPP_Fusion Not yet run
unverified (harvested, no recorded run)
addisonwang2013/DTL/modeling/deeplab_dtl.py
code served (permissive licence) · get_code("15fc6f001d543fef")
How it ran

no invocation recorded.

DeepLab_Dual_V2 Not yet run
unverified (harvested, no recorded run)
addisonwang2013/DTL/modeling/deeplab_dtl.py
code served (permissive licence) · get_code("2db744a03f84a236")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 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
conv3x3 6 other papers
5 dated earlier, 1 later
1808.07535 (2018-08)
Learning Hierarchical Semantic Image Manipulation through Structured Representations
1906.05856 (2019-06)
Detecting Photoshopped Faces by Scripting Photoshop
1908.06702 (2019-08)
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path
and 3 more not named here
fixed_padding 3 other papers
3 dated earlier
1901.04056 (2019-01)
The Liver Tumor Segmentation Benchmark (LiTS)
2003.05970 (2020-03)
LiDAR guided Small obstacle Segmentation
2104.06394 (2021-04)
All you need are a few pixels: semantic segmentation with PixelPick
conv_bn 2 other papers
2 dated earlier
2003.05970 (2020-03)
LiDAR guided Small obstacle Segmentation
2104.06394 (2021-04)
All you need are a few pixels: semantic segmentation with PixelPick

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

Event cameras are novel sensors that perceive the perpixel intensity changes and output asynchronous event streams with high dynamic range and less motion blur. It has been shown that events alone can be used for end-task learning, e.g., semantic segmentation, based on encoderdecoder-like networks. However, as events are sparse and mostly reflect edge information, it is difficult to recover original details merely relying on the decoder. Moreover, most methods resort to the pixel-wise loss alone for supervision, which might be insufficient to fully exploit the visual details from sparse events, thus leading to less optimal performance. In this paper, we propose a simple yet flexible twostream framework named Dual Transfer Learning (DTL) to effectively enhance the performance on the end-tasks without adding extra inference cost. The proposed approach consists of three parts: event to end-task learning (EEL) branch, event to image translation (EIT) branch, and transfer learning (TL) module that simultaneously explores the feature-level affinity information and pixel-level knowledge from the EIT branch to improve the EEL branch. This simple yet novel method leads to strong representation learning from events and is evidenced by the significant performance boost on the end-tasks such as semantic segmentation and depth estimation.

For agents

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

get_harvested_code_for_paper("2109.01801")
get_code_for_paper("2109.01801")
have("2109.01801")

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

curl https://syntology.ai/api/ran/2109.01801.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.01801.svg)](https://syntology.ai/paper/2109.01801)

Connect an agent — have() is free.