SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.02366 · CVPR · 2021

Neural Feature Search for RGB-Infrared Person Re-Identification

Lin Wan, Zhihang Li, Yehansen Chen, Qianyan Jing, Zongyuan Sun

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 6 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/2104.02366.json · badge: /api/ran/2104.02366.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
mangye16/Cross-Modal-Re-ID-baseline community
Papers with Code archive
5 ran · 6 no recorded run
FunctionStatusWhere it lives
Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("1ac2e5df7496b629")
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, Bottleneck: 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 downsample module that matches the expected input/output
downsample = nn.Sequential(
    nn.Conv2d(4, 16, kernel_size=1, stride=2, bias=False),
    nn.BatchNorm2d(16)
)

ARGS = {
    "inplanes": 4,
    "planes": 4,
    "stride": 2,
    "downsample": downsample,
    "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 Bottleneck — 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 Bottleneck 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
Non_local Ran
ran on a synthesized input · constructed an object; no result was computed
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("39bc57088adc1df1")
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, Non_local: 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 = {
    "in_channels": 8,
    "reduc_ratio": 2,
}
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 Non_local — 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 Non_local 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
ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("be06126c93d1a123")
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, ResNet: 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
import math

torch.manual_seed(0)

# Define a minimal block class that satisfies the ResNet usage
class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, downsample=None, dilation=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=dilation, dilation=dilation, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride
    
    def forward(self, x):
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out

ARGS = {
    'block': BasicBlock,
    'layers': [2, 2, 2, 2],
    'last_conv_stride': 2,
    'last_conv_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 ResNet — 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 ResNet 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
remove_fc Ran
ran; our contract draft was wrong, not the code
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("c5961f4478deab2b")
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 dict. 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 state_dict with both fc layer parameters and other parameters
state_dict = {
    'conv1.weight': torch.randn(4, 3, 3, 3),
    'conv1.bias': torch.randn(4),
    'fc.weight': torch.randn(10, 4),
    'fc.bias': torch.randn(10),
    'fc.layer2.weight': torch.randn(5, 10),
    'linear.weight': torch.randn(2, 4),
    'linear.bias': torch.randn(2),
}

ARGS = {
    'state_dict': state_dict
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
resnet50 Ran
ran; our contract draft was wrong, not the code
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("cbefb8091a472844")
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 ResNet. 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 = {
    '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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
base_resnet Not yet run
unverified (harvested, no recorded run)
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("808abc324b799b4f")
How it ran

no invocation recorded.

embed_net Not yet run
unverified (harvested, no recorded run)
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("407a970ea30aea78")
How it ran

no invocation recorded.

thermal_module Not yet run
unverified (harvested, no recorded run)
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("05cc6196c717f836")
How it ran

no invocation recorded.

visible_module Not yet run
unverified (harvested, no recorded run)
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("1c67d33e697b6c55")
How it ran

no invocation recorded.

weights_init_classifier Not yet run
unverified (harvested, no recorded run)
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("acca42c3caaebbf2")
How it ran

no invocation recorded.

weights_init_kaiming Not yet run
unverified (harvested, no recorded run)
mangye16/Cross-Modal-Re-ID-baseline/ICCV21_CAJ/model.py
code served (permissive licence) · get_code("d110187b453d6759")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 9 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 9 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.

FunctionAlso present inEarliest-datedOthers named
remove_fc
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 2 only as an assembly brick
2101.08467 (2021-01)
CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
weights_init_kaiming
brick of this paper's assembly: helper
3 other papers
3 later · 3 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2303.14481 (2023-03)
Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
Bottleneck
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
ResNet
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
resnet50
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
thermal_module
brick of this paper's assembly: model
2 other papers
2 later · 2 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
visible_module
brick of this paper's assembly: model
2 other papers
2 later · 2 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
weights_init_classifier
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2208.02450 (2022-08)
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
base_resnet
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2411.01225 (2024-11)
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification

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

) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared camera views. Most existing works achieve performance gains through manually-designed feature selection modules, which often require significant domain knowledge and rich experience. In this paper, we study a general paradigm, termed Neural Feature Search (NFS), to automate the process of feature selection. Specifically, NFS combines a duallevel feature search space and a differentiable search strategy to jointly select identity-related cues in coarse-grained channels and fine-grained spatial pixels. This combination allows NFS to adaptively filter background noises and concentrate on informative parts of human bodies in a datadriven manner. Moreover, a cross-modality contrastive optimization scheme further guides NFS to search features that can minimize modality discrepancy whilst maximizing inter-class distance. Extensive experiments on mainstream benchmarks demonstrate that our method outperforms state-of-the-arts, especially achieving better performance on the RegDB dataset with significant improvement of 11. respectively.

For agents

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

get_harvested_code_for_paper("2104.02366")
get_code_for_paper("2104.02366")
have("2104.02366")

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

curl https://syntology.ai/api/ran/2104.02366.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.02366.svg)](https://syntology.ai/paper/2104.02366)

Connect an agent — have() is free.